@aeye/models 0.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (74) hide show
  1. package/ReplicateScrape.md +54 -0
  2. package/dist/scripts/codegen.d.ts +21 -0
  3. package/dist/scripts/codegen.d.ts.map +1 -0
  4. package/dist/scripts/codegen.js +102 -0
  5. package/dist/scripts/codegen.js.map +1 -0
  6. package/dist/scripts/scrape.d.ts +19 -0
  7. package/dist/scripts/scrape.d.ts.map +1 -0
  8. package/dist/scripts/scrape.js +146 -0
  9. package/dist/scripts/scrape.js.map +1 -0
  10. package/dist/scripts/scrapers/__tests__/aws.test.d.ts +8 -0
  11. package/dist/scripts/scrapers/__tests__/aws.test.d.ts.map +1 -0
  12. package/dist/scripts/scrapers/__tests__/aws.test.js +73 -0
  13. package/dist/scripts/scrapers/__tests__/aws.test.js.map +1 -0
  14. package/dist/scripts/scrapers/aws.d.ts +12 -0
  15. package/dist/scripts/scrapers/aws.d.ts.map +1 -0
  16. package/dist/scripts/scrapers/aws.js +314 -0
  17. package/dist/scripts/scrapers/aws.js.map +1 -0
  18. package/dist/scripts/scrapers/openai.d.ts +12 -0
  19. package/dist/scripts/scrapers/openai.d.ts.map +1 -0
  20. package/dist/scripts/scrapers/openai.js +490 -0
  21. package/dist/scripts/scrapers/openai.js.map +1 -0
  22. package/dist/scripts/scrapers/openrouter.d.ts +13 -0
  23. package/dist/scripts/scrapers/openrouter.d.ts.map +1 -0
  24. package/dist/scripts/scrapers/openrouter.js +156 -0
  25. package/dist/scripts/scrapers/openrouter.js.map +1 -0
  26. package/dist/scripts/scrapers/replicate.d.ts +12 -0
  27. package/dist/scripts/scrapers/replicate.d.ts.map +1 -0
  28. package/dist/scripts/scrapers/replicate.js +305 -0
  29. package/dist/scripts/scrapers/replicate.js.map +1 -0
  30. package/dist/src/index.d.ts +11 -0
  31. package/dist/src/index.d.ts.map +1 -0
  32. package/dist/src/index.js +11 -0
  33. package/dist/src/index.js.map +1 -0
  34. package/dist/src/models/aws.d.ts +11 -0
  35. package/dist/src/models/aws.d.ts.map +1 -0
  36. package/dist/src/models/aws.js +2632 -0
  37. package/dist/src/models/aws.js.map +1 -0
  38. package/dist/src/models/index.d.ts +15 -0
  39. package/dist/src/models/index.d.ts.map +1 -0
  40. package/dist/src/models/index.js +18 -0
  41. package/dist/src/models/index.js.map +1 -0
  42. package/dist/src/models/openai.d.ts +11 -0
  43. package/dist/src/models/openai.d.ts.map +1 -0
  44. package/dist/src/models/openai.js +2207 -0
  45. package/dist/src/models/openai.js.map +1 -0
  46. package/dist/src/models/openrouter.d.ts +11 -0
  47. package/dist/src/models/openrouter.d.ts.map +1 -0
  48. package/dist/src/models/openrouter.js +9786 -0
  49. package/dist/src/models/openrouter.js.map +1 -0
  50. package/dist/src/models/replicate.d.ts +11 -0
  51. package/dist/src/models/replicate.d.ts.map +1 -0
  52. package/dist/src/models/replicate.js +4106 -0
  53. package/dist/src/models/replicate.js.map +1 -0
  54. package/dist/src/transformers/index.d.ts +23 -0
  55. package/dist/src/transformers/index.d.ts.map +1 -0
  56. package/dist/src/transformers/index.js +24 -0
  57. package/dist/src/transformers/index.js.map +1 -0
  58. package/package.json +50 -0
  59. package/scripts/codegen.ts +117 -0
  60. package/scripts/scrape.ts +182 -0
  61. package/scripts/scrapers/__tests__/aws.test.ts +86 -0
  62. package/scripts/scrapers/aws.ts +370 -0
  63. package/scripts/scrapers/openai.ts +619 -0
  64. package/scripts/scrapers/openrouter.ts +214 -0
  65. package/scripts/scrapers/replicate.ts +448 -0
  66. package/scripts/tsconfig.json +24 -0
  67. package/src/index.ts +11 -0
  68. package/src/models/aws.ts +2634 -0
  69. package/src/models/index.ts +21 -0
  70. package/src/models/openai.ts +2209 -0
  71. package/src/models/openrouter.ts +9788 -0
  72. package/src/models/replicate.ts +4108 -0
  73. package/src/transformers/index.ts +26 -0
  74. package/tsconfig.json +14 -0
@@ -0,0 +1,4106 @@
1
+ /**
2
+ * Generated model data
3
+ *
4
+ * This file is auto-generated by the scraper scripts.
5
+ * Do not edit manually - your changes will be overwritten.
6
+ *
7
+ * To regenerate, run: npm run scrape
8
+ */
9
+ export const replicateModels = [{
10
+ id: 'ideogram-ai/ideogram-v2a',
11
+ provider: 'replicate',
12
+ name: 'ideogram-v2a',
13
+ contextWindow: 0,
14
+ tier: 'flagship',
15
+ capabilities: new Set(['chat']),
16
+ pricing: {},
17
+ metadata: {
18
+ owner: "ideogram-ai",
19
+ description: "Like Ideogram v2, but faster and cheaper",
20
+ runCount: 1772190,
21
+ githubUrl: null,
22
+ visibility: "public",
23
+ source: "replicate",
24
+ latestVersionId: "5b35cd83557325651e9f0165c6efba598caae0c53620c3dab83e8d6815d456b9",
25
+ cogVersion: "0.16.7"
26
+ }
27
+ }, {
28
+ id: 'ideogram-ai/ideogram-v2a-turbo',
29
+ provider: 'replicate',
30
+ name: 'ideogram-v2a-turbo',
31
+ contextWindow: 0,
32
+ tier: 'flagship',
33
+ capabilities: new Set(['chat']),
34
+ pricing: {},
35
+ metadata: {
36
+ owner: "ideogram-ai",
37
+ description: "Like Ideogram v2 turbo, but now faster and cheaper",
38
+ runCount: 359038,
39
+ githubUrl: null,
40
+ visibility: "public",
41
+ source: "replicate",
42
+ latestVersionId: "58823226f47daa9f3e3729448d2d2c2a72f80df0d671b3fe0d07edb6f8ffd3f9",
43
+ cogVersion: "0.16.7"
44
+ }
45
+ }, {
46
+ id: 'minimax/image-01',
47
+ provider: 'replicate',
48
+ name: 'image-01',
49
+ contextWindow: 0,
50
+ tier: 'flagship',
51
+ capabilities: new Set(['chat']),
52
+ pricing: {},
53
+ metadata: {
54
+ owner: "minimax",
55
+ description: "Minimax's first image model, with character reference support",
56
+ runCount: 1872600,
57
+ githubUrl: null,
58
+ visibility: "public",
59
+ source: "replicate",
60
+ latestVersionId: "47ca89ad46682c1dd0ca335601cd7ea2eb10fb94ce4e0a5abafa7e74f23ae7b6",
61
+ cogVersion: "0.16.7"
62
+ }
63
+ }, {
64
+ id: 'bytedance/seedream-3',
65
+ provider: 'replicate',
66
+ name: 'seedream-3',
67
+ contextWindow: 0,
68
+ tier: 'flagship',
69
+ capabilities: new Set(['image']),
70
+ pricing: {},
71
+ metadata: {
72
+ owner: "bytedance",
73
+ description: "A text-to-image model with support for native high-resolution (2K) image generation",
74
+ runCount: 2753484,
75
+ githubUrl: null,
76
+ visibility: "public",
77
+ source: "replicate",
78
+ latestVersionId: "2684dbb067ec276430591d86390a023ea47dd7e3c46902f8f823983a1aae5437",
79
+ cogVersion: "0.16.8"
80
+ }
81
+ }, {
82
+ id: 'luma/photon',
83
+ provider: 'replicate',
84
+ name: 'photon',
85
+ contextWindow: 0,
86
+ tier: 'flagship',
87
+ capabilities: new Set(['image']),
88
+ pricing: {},
89
+ metadata: {
90
+ owner: "luma",
91
+ description: "High-quality image generation model optimized for creative professional workflows and ultra-high fidelity outputs",
92
+ runCount: 2945427,
93
+ githubUrl: null,
94
+ visibility: "public",
95
+ source: "replicate",
96
+ latestVersionId: "fe142c037cf359764f2058c3a42ef0dc750d908311d02868cbc7769fe800b648",
97
+ cogVersion: "0.10.0-alpha27"
98
+ }
99
+ }, {
100
+ id: 'luma/photon-flash',
101
+ provider: 'replicate',
102
+ name: 'photon-flash',
103
+ contextWindow: 0,
104
+ tier: 'flagship',
105
+ capabilities: new Set(['chat']),
106
+ pricing: {},
107
+ metadata: {
108
+ owner: "luma",
109
+ description: "Accelerated variant of Photon prioritizing speed while maintaining quality",
110
+ runCount: 177144,
111
+ githubUrl: null,
112
+ visibility: "public",
113
+ source: "replicate",
114
+ latestVersionId: "66b533244766eb25d4fe3306a1986d930c9e49be6044a85213daa3f9393b1fe2",
115
+ cogVersion: "0.16.8"
116
+ }
117
+ }, {
118
+ id: 'prunaai/hidream-l1-full',
119
+ provider: 'replicate',
120
+ name: 'hidream-l1-full',
121
+ contextWindow: 0,
122
+ tier: 'flagship',
123
+ capabilities: new Set(['chat']),
124
+ pricing: {},
125
+ metadata: {
126
+ owner: "prunaai",
127
+ description: "This is an optimised version of the hidream-full model using the pruna ai optimisation toolkit!",
128
+ runCount: 29552,
129
+ githubUrl: null,
130
+ visibility: "public",
131
+ source: "replicate",
132
+ latestVersionId: "03d58532fd29e39fd2ed80e86c3da1cebec28ef2734081cf1366710d30388f42",
133
+ cogVersion: "0.14.7"
134
+ }
135
+ }, {
136
+ id: 'google/imagen-4-fast',
137
+ provider: 'replicate',
138
+ name: 'imagen-4-fast',
139
+ contextWindow: 0,
140
+ tier: 'flagship',
141
+ capabilities: new Set(['image']),
142
+ pricing: {},
143
+ metadata: {
144
+ owner: "google",
145
+ description: "Use this fast version of Imagen 4 when speed and cost are more important than quality",
146
+ runCount: 1516842,
147
+ githubUrl: null,
148
+ visibility: "public",
149
+ source: "replicate",
150
+ latestVersionId: "c7ac6d10969b5c36d9eca1f5ece370aba38ca06d6477769d7c1cde84746d574a",
151
+ cogVersion: "0.16.8"
152
+ }
153
+ }, {
154
+ id: 'google/imagen-4-ultra',
155
+ provider: 'replicate',
156
+ name: 'imagen-4-ultra',
157
+ contextWindow: 0,
158
+ tier: 'flagship',
159
+ capabilities: new Set(['image']),
160
+ pricing: {},
161
+ metadata: {
162
+ owner: "google",
163
+ description: "Use this ultra version of Imagen 4 when quality matters more than speed and cost",
164
+ runCount: 921790,
165
+ githubUrl: null,
166
+ visibility: "public",
167
+ source: "replicate",
168
+ latestVersionId: "8cffb16c5120dea414b15571431390ae32ee5c8cd38ea11ea0288e6b550ef162",
169
+ cogVersion: "0.16.8"
170
+ }
171
+ }, {
172
+ id: 'nvidia/sana-sprint-1.6b',
173
+ provider: 'replicate',
174
+ name: 'sana-sprint-1.6b',
175
+ contextWindow: 0,
176
+ tier: 'flagship',
177
+ capabilities: new Set(['chat']),
178
+ pricing: {},
179
+ metadata: {
180
+ owner: "nvidia",
181
+ description: "SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation",
182
+ runCount: 805553,
183
+ githubUrl: "https://github.com/lucataco/cog-sana-sprint-1.6b",
184
+ visibility: "public",
185
+ source: "replicate",
186
+ latestVersionId: "038aee6907b53a5c148780983e39a50ce7cd0747b4e2642e78387f48cf36039a",
187
+ cogVersion: "0.16.0"
188
+ }
189
+ }, {
190
+ id: 'prunaai/hidream-l1-dev',
191
+ provider: 'replicate',
192
+ name: 'hidream-l1-dev',
193
+ contextWindow: 0,
194
+ tier: 'flagship',
195
+ capabilities: new Set(['chat']),
196
+ pricing: {},
197
+ metadata: {
198
+ owner: "prunaai",
199
+ description: "This is an optimised version of the hidream-l1-dev model using the pruna ai optimisation toolkit!",
200
+ runCount: 43938,
201
+ githubUrl: null,
202
+ visibility: "public",
203
+ source: "replicate",
204
+ latestVersionId: "4dfcd146c0def4812455415f55556f6bc84025dcb15193cf1977f01bd384d191",
205
+ cogVersion: "0.14.7"
206
+ }
207
+ }, {
208
+ id: 'prunaai/hidream-l1-fast',
209
+ provider: 'replicate',
210
+ name: 'hidream-l1-fast',
211
+ contextWindow: 0,
212
+ tier: 'flagship',
213
+ capabilities: new Set(['chat']),
214
+ pricing: {},
215
+ metadata: {
216
+ owner: "prunaai",
217
+ description: "This is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!",
218
+ runCount: 4535632,
219
+ githubUrl: "https://github.com/HiDream-ai/HiDream-I1",
220
+ visibility: "public",
221
+ source: "replicate",
222
+ latestVersionId: "06898b39cb00e42d31666b0dc8b9904f326169768129d756184f65ecf1986c8f",
223
+ cogVersion: "0.16.0"
224
+ }
225
+ }, {
226
+ id: 'prunaai/flux.1-dev',
227
+ provider: 'replicate',
228
+ name: 'flux.1-dev',
229
+ contextWindow: 0,
230
+ tier: 'flagship',
231
+ capabilities: new Set(['image']),
232
+ pricing: {},
233
+ metadata: {
234
+ owner: "prunaai",
235
+ description: "This is the fastest Flux Dev endpoint in the world, contact us for more at pruna.ai",
236
+ runCount: 28096525,
237
+ githubUrl: "https://github.com/black-forest-labs/flux",
238
+ visibility: "public",
239
+ source: "replicate",
240
+ latestVersionId: "b0306d92aa025bb747dc74162f3c27d6ed83798e08e5f8977adf3d859d0536a3",
241
+ cogVersion: "0.14.7"
242
+ }
243
+ }, {
244
+ id: 'prunaai/sdxl-lightning',
245
+ provider: 'replicate',
246
+ name: 'sdxl-lightning',
247
+ contextWindow: 0,
248
+ tier: 'flagship',
249
+ capabilities: new Set(['image']),
250
+ pricing: {},
251
+ metadata: {
252
+ owner: "prunaai",
253
+ description: "This is the fastest sdxl-lightning endpoint in the world on A100, contact us for more at pruna.ai",
254
+ runCount: 669,
255
+ githubUrl: null,
256
+ visibility: "public",
257
+ source: "replicate",
258
+ latestVersionId: "123d4264aec4d1c81d8bf142e0d90d6fd4c346f1a869406019f6d1653882d7c3",
259
+ cogVersion: "0.14.7"
260
+ }
261
+ }, {
262
+ id: 'ideogram-ai/ideogram-v3-quality',
263
+ provider: 'replicate',
264
+ name: 'ideogram-v3-quality',
265
+ contextWindow: 0,
266
+ tier: 'flagship',
267
+ capabilities: new Set(['chat']),
268
+ pricing: {},
269
+ metadata: {
270
+ owner: "ideogram-ai",
271
+ description: "The highest quality Ideogram v3 model. v3 creates images with stunning realism, creative designs, and consistent styles",
272
+ runCount: 1921177,
273
+ githubUrl: null,
274
+ visibility: "public",
275
+ source: "replicate",
276
+ latestVersionId: "7d53dd52ee9b5ed39b36df6d7de2bec21d075e51286919055c7adcda922d1e20",
277
+ cogVersion: "0.16.7"
278
+ }
279
+ }, {
280
+ id: 'ideogram-ai/ideogram-v3-turbo',
281
+ provider: 'replicate',
282
+ name: 'ideogram-v3-turbo',
283
+ contextWindow: 0,
284
+ tier: 'flagship',
285
+ capabilities: new Set(['chat']),
286
+ pricing: {},
287
+ metadata: {
288
+ owner: "ideogram-ai",
289
+ description: "Turbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles",
290
+ runCount: 3509453,
291
+ githubUrl: null,
292
+ visibility: "public",
293
+ source: "replicate",
294
+ latestVersionId: "1d41d0ce51940176325346f5c614e81f1e2ee6f5f2b26c6e36f7d7b484af37be",
295
+ cogVersion: "0.16.7"
296
+ }
297
+ }, {
298
+ id: 'ideogram-ai/ideogram-v3-balanced',
299
+ provider: 'replicate',
300
+ name: 'ideogram-v3-balanced',
301
+ contextWindow: 0,
302
+ tier: 'flagship',
303
+ capabilities: new Set(['chat']),
304
+ pricing: {},
305
+ metadata: {
306
+ owner: "ideogram-ai",
307
+ description: "Balance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles",
308
+ runCount: 286659,
309
+ githubUrl: null,
310
+ visibility: "public",
311
+ source: "replicate",
312
+ latestVersionId: "7f00c6f29324fb51a748bb7dafc205456f850d7320e54db3ae78a2cbded4ab20",
313
+ cogVersion: "0.16.7"
314
+ }
315
+ }, {
316
+ id: 'black-forest-labs/flux-dev-lora',
317
+ provider: 'replicate',
318
+ name: 'flux-dev-lora',
319
+ contextWindow: 0,
320
+ tier: 'flagship',
321
+ capabilities: new Set(['image']),
322
+ pricing: {},
323
+ metadata: {
324
+ owner: "black-forest-labs",
325
+ description: "A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference",
326
+ runCount: 4823245,
327
+ githubUrl: "https://github.com/replicate/cog-flux",
328
+ visibility: "public",
329
+ source: "replicate",
330
+ latestVersionId: "ae0d7d645446924cf1871e3ca8796e8318f72465d2b5af9323a835df93bf0917",
331
+ cogVersion: "0.15.8"
332
+ }
333
+ }, {
334
+ id: 'bria/image-3.2',
335
+ provider: 'replicate',
336
+ name: 'image-3.2',
337
+ contextWindow: 0,
338
+ tier: 'flagship',
339
+ capabilities: new Set(['image']),
340
+ pricing: {},
341
+ metadata: {
342
+ owner: "bria",
343
+ description: "Commercial-ready, trained entirely on licensed data, text-to-image model. With only 4B parameters provides exceptional aesthetics and text rendering. Evaluated to be on par to other leading models in the market",
344
+ runCount: 40322,
345
+ githubUrl: null,
346
+ visibility: "public",
347
+ source: "replicate",
348
+ latestVersionId: "20c9aac6ff4fb6aca8b404ac4c010dae1abfda825a96c37554d833f0238d892e",
349
+ cogVersion: "0.16.7"
350
+ }
351
+ }, {
352
+ id: 'google/imagen-4',
353
+ provider: 'replicate',
354
+ name: 'imagen-4',
355
+ contextWindow: 0,
356
+ tier: 'flagship',
357
+ capabilities: new Set(['image']),
358
+ pricing: {},
359
+ metadata: {
360
+ owner: "google",
361
+ description: "Google's Imagen 4 flagship model",
362
+ runCount: 5072398,
363
+ githubUrl: null,
364
+ visibility: "public",
365
+ source: "replicate",
366
+ latestVersionId: "6ced47473a9ac48a8bfba0981dccc54c41e3029d169114d1991dfd15aeb4a5c4",
367
+ cogVersion: "0.16.8"
368
+ }
369
+ }, {
370
+ id: 'black-forest-labs/flux-kontext-pro',
371
+ provider: 'replicate',
372
+ name: 'flux-kontext-pro',
373
+ contextWindow: 0,
374
+ tier: 'flagship',
375
+ capabilities: new Set(['image']),
376
+ pricing: {},
377
+ metadata: {
378
+ owner: "black-forest-labs",
379
+ description: "A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language",
380
+ runCount: 30622186,
381
+ githubUrl: null,
382
+ visibility: "public",
383
+ source: "replicate",
384
+ latestVersionId: "2dfe45debca13e5ecfad755ef6ca9943fc56a6effb306f4c6e2ea4762df6e53e",
385
+ cogVersion: "0.16.6"
386
+ }
387
+ }, {
388
+ id: 'black-forest-labs/flux-kontext-max',
389
+ provider: 'replicate',
390
+ name: 'flux-kontext-max',
391
+ contextWindow: 0,
392
+ tier: 'flagship',
393
+ capabilities: new Set(['image']),
394
+ pricing: {},
395
+ metadata: {
396
+ owner: "black-forest-labs",
397
+ description: "A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts",
398
+ runCount: 7437526,
399
+ githubUrl: null,
400
+ visibility: "public",
401
+ source: "replicate",
402
+ latestVersionId: "f72e27297d9c05a36b7fd8faff393d31e3b368543e0bc44bde521886700e166c",
403
+ cogVersion: "0.16.0"
404
+ }
405
+ }, {
406
+ id: 'prunaai/wan-2.2-image',
407
+ provider: 'replicate',
408
+ name: 'wan-2.2-image',
409
+ contextWindow: 0,
410
+ tier: 'flagship',
411
+ capabilities: new Set(['chat']),
412
+ pricing: {},
413
+ metadata: {
414
+ owner: "prunaai",
415
+ description: "This model generates beautiful cinematic 2 megapixel images in 3-4 seconds and is derived from the Wan 2.2 model through optimisation techniques from the pruna package",
416
+ runCount: 659133,
417
+ githubUrl: null,
418
+ visibility: "public",
419
+ source: "replicate",
420
+ latestVersionId: "16e15e913fcc71c1a5defb335ea84739f99731fa1ee17995117c7d9adc6d176c",
421
+ cogVersion: "0.14.7"
422
+ }
423
+ }, {
424
+ id: 'qwen/qwen-image',
425
+ provider: 'replicate',
426
+ name: 'qwen-image',
427
+ contextWindow: 0,
428
+ tier: 'flagship',
429
+ capabilities: new Set(['image']),
430
+ pricing: {},
431
+ metadata: {
432
+ owner: "qwen",
433
+ description: "An image generation foundation model in the Qwen series that achieves significant advances in complex text rendering.",
434
+ runCount: 805313,
435
+ githubUrl: "https://github.com/QwenLM/Qwen-Image",
436
+ visibility: "public",
437
+ source: "replicate",
438
+ latestVersionId: "905e345fe1dfe10d628daac2140dd8dea471c0d99793ef0fdc46a15c688b62fb",
439
+ cogVersion: "0.16.0"
440
+ }
441
+ }, {
442
+ id: 'bytedance/seedream-4',
443
+ provider: 'replicate',
444
+ name: 'seedream-4',
445
+ contextWindow: 0,
446
+ tier: 'flagship',
447
+ capabilities: new Set(['image']),
448
+ pricing: {},
449
+ metadata: {
450
+ owner: "bytedance",
451
+ description: "Unified text-to-image generation and precise single-sentence editing at up to 4K resolution",
452
+ runCount: 5104501,
453
+ githubUrl: null,
454
+ visibility: "public",
455
+ source: "replicate",
456
+ latestVersionId: "b2d15affd5864f968fd20331de1e1e5d510ab7853f90a7d0836984871224a9fc",
457
+ cogVersion: "0.16.8"
458
+ }
459
+ }, {
460
+ id: 'google/nano-banana',
461
+ provider: 'replicate',
462
+ name: 'nano-banana',
463
+ contextWindow: 0,
464
+ tier: 'flagship',
465
+ capabilities: new Set(['vision', 'image']),
466
+ pricing: {},
467
+ metadata: {
468
+ owner: "google",
469
+ description: "Google's latest image editing model in Gemini 2.5",
470
+ runCount: 25709809,
471
+ githubUrl: null,
472
+ visibility: "public",
473
+ source: "replicate",
474
+ latestVersionId: "2c8a3b5b81554aa195bde461e2caa6afacd69a66c48a64fb0e650c9789f8b8a0",
475
+ cogVersion: "0.16.8"
476
+ }
477
+ }, {
478
+ id: 'google/imagen-3',
479
+ provider: 'replicate',
480
+ name: 'imagen-3',
481
+ contextWindow: 0,
482
+ tier: 'flagship',
483
+ capabilities: new Set(['image']),
484
+ pricing: {},
485
+ metadata: {
486
+ owner: "google",
487
+ description: "Google's highest quality text-to-image model, capable of generating images with detail, rich lighting and beauty",
488
+ runCount: 1705140,
489
+ githubUrl: null,
490
+ visibility: "public",
491
+ source: "replicate",
492
+ latestVersionId: "7a9544a6178a1bf96e4a71deaac8b08fbf8fac37096c69fe8b80a7aeaf4cdbec",
493
+ cogVersion: "0.16.7"
494
+ }
495
+ }, {
496
+ id: 'google/imagen-3-fast',
497
+ provider: 'replicate',
498
+ name: 'imagen-3-fast',
499
+ contextWindow: 0,
500
+ tier: 'flagship',
501
+ capabilities: new Set(['image']),
502
+ pricing: {},
503
+ metadata: {
504
+ owner: "google",
505
+ description: "A faster and cheaper Imagen 3 model, for when price or speed are more important than final image quality",
506
+ runCount: 448735,
507
+ githubUrl: null,
508
+ visibility: "public",
509
+ source: "replicate",
510
+ latestVersionId: "822bf2627015139af9967f9e5ad014d22311012fdd5db56ab7783c7dd524f1c1",
511
+ cogVersion: "0.16.8"
512
+ }
513
+ }, {
514
+ id: 'tencent/hunyuan-image-3',
515
+ provider: 'replicate',
516
+ name: 'hunyuan-image-3',
517
+ contextWindow: 0,
518
+ tier: 'flagship',
519
+ capabilities: new Set(['image']),
520
+ pricing: {},
521
+ metadata: {
522
+ owner: "tencent",
523
+ description: "A powerful native multimodal model for image generation (PrunaAI squeezed)",
524
+ runCount: 12857,
525
+ githubUrl: "https://github.com/Tencent-Hunyuan/HunyuanImage-3.0",
526
+ visibility: "public",
527
+ source: "replicate",
528
+ latestVersionId: "080dbbefcd1504ca5aeebaa2815fd51467d5bb793d2b1fb4eb4eb32ac22a3377",
529
+ cogVersion: "0.16.7"
530
+ }
531
+ }, {
532
+ id: 'leonardoai/lucid-origin',
533
+ provider: 'replicate',
534
+ name: 'lucid-origin',
535
+ contextWindow: 0,
536
+ tier: 'flagship',
537
+ capabilities: new Set(['chat']),
538
+ pricing: {},
539
+ metadata: {
540
+ owner: "leonardoai",
541
+ description: "Artistic and high-quality visuals with improved prompt adherence, diversity, and definition",
542
+ runCount: 87679,
543
+ githubUrl: null,
544
+ visibility: "public",
545
+ source: "replicate",
546
+ latestVersionId: "d0a4e1b532c680aa4c8f869d9c72070b694f4b439ba9a38c35c706e323e8839e",
547
+ cogVersion: "0.16.7"
548
+ }
549
+ }, {
550
+ id: 'ai-forever/kandinsky-2',
551
+ provider: 'replicate',
552
+ name: 'kandinsky-2',
553
+ contextWindow: 0,
554
+ tier: 'flagship',
555
+ capabilities: new Set(['chat']),
556
+ pricing: {},
557
+ metadata: {
558
+ owner: "ai-forever",
559
+ description: "text2img model trained on LAION HighRes and fine-tuned on internal datasets",
560
+ runCount: 6180104,
561
+ githubUrl: "https://github.com/chenxwh/Kandinsky-2",
562
+ visibility: "public",
563
+ source: "replicate",
564
+ latestVersionId: "3c6374e7a9a17e01afe306a5218cc67de55b19ea536466d6ea2602cfecea40a9",
565
+ cogVersion: "v0.9.5+dev"
566
+ }
567
+ }, {
568
+ id: 'lucataco/ssd-1b',
569
+ provider: 'replicate',
570
+ name: 'ssd-1b',
571
+ contextWindow: 0,
572
+ tier: 'flagship',
573
+ capabilities: new Set(['image']),
574
+ pricing: {},
575
+ metadata: {
576
+ owner: "lucataco",
577
+ description: "Segmind Stable Diffusion Model (SSD-1B) is a distilled 50% smaller version of SDXL, offering a 60% speedup while maintaining high-quality text-to-image generation capabilities",
578
+ runCount: 1034799,
579
+ githubUrl: "https://github.com/lucataco/cog-ssd-1b",
580
+ visibility: "public",
581
+ source: "replicate",
582
+ latestVersionId: "b19e3639452c59ce8295b82aba70a231404cb062f2eb580ea894b31e8ce5bbb6",
583
+ cogVersion: "0.8.5"
584
+ }
585
+ }, {
586
+ id: 'fofr/any-comfyui-workflow',
587
+ provider: 'replicate',
588
+ name: 'any-comfyui-workflow',
589
+ contextWindow: 0,
590
+ tier: 'flagship',
591
+ capabilities: new Set(['chat']),
592
+ pricing: {},
593
+ metadata: {
594
+ owner: "fofr",
595
+ description: "Run any ComfyUI workflow. Guide: https://github.com/replicate/cog-comfyui",
596
+ runCount: 6813323,
597
+ githubUrl: "https://github.com/replicate/cog-comfyui",
598
+ visibility: "public",
599
+ source: "replicate",
600
+ latestVersionId: "67ed4ba04ce0842446e16c428b1be131452815d01810861f71d171f63e8ba8f0",
601
+ cogVersion: "0.15.9"
602
+ }
603
+ }, {
604
+ id: 'black-forest-labs/flux-dev',
605
+ provider: 'replicate',
606
+ name: 'flux-dev',
607
+ contextWindow: 0,
608
+ tier: 'flagship',
609
+ capabilities: new Set(['image']),
610
+ pricing: {},
611
+ metadata: {
612
+ owner: "black-forest-labs",
613
+ description: "A 12 billion parameter rectified flow transformer capable of generating images from text descriptions",
614
+ runCount: 29817386,
615
+ githubUrl: "https://github.com/replicate/cog-flux",
616
+ visibility: "public",
617
+ source: "replicate",
618
+ latestVersionId: "6e4a938f85952bdabcc15aa329178c4d681c52bf25a0342403287dc26944661d",
619
+ cogVersion: "0.15.8"
620
+ }
621
+ }, {
622
+ id: 'ideogram-ai/ideogram-v2-turbo',
623
+ provider: 'replicate',
624
+ name: 'ideogram-v2-turbo',
625
+ contextWindow: 0,
626
+ tier: 'flagship',
627
+ capabilities: new Set(['chat']),
628
+ pricing: {},
629
+ metadata: {
630
+ owner: "ideogram-ai",
631
+ description: "A fast image model with state of the art inpainting, prompt comprehension and text rendering.",
632
+ runCount: 2672551,
633
+ githubUrl: null,
634
+ visibility: "public",
635
+ source: "replicate",
636
+ latestVersionId: "304626064ece87e5cd7598fad9d5bc85d22750812c9b3821f8b133b832293192",
637
+ cogVersion: "0.16.7"
638
+ }
639
+ }, {
640
+ id: 'datacte/proteus-v0.3',
641
+ provider: 'replicate',
642
+ name: 'proteus-v0.3',
643
+ contextWindow: 0,
644
+ tier: 'flagship',
645
+ capabilities: new Set(['chat']),
646
+ pricing: {},
647
+ metadata: {
648
+ owner: "datacte",
649
+ description: "ProteusV0.3: The Anime Update",
650
+ runCount: 4668655,
651
+ githubUrl: "https://github.com/lucataco/cog-proteus-v0.3",
652
+ visibility: "public",
653
+ source: "replicate",
654
+ latestVersionId: "b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48",
655
+ cogVersion: "0.9.3"
656
+ }
657
+ }, {
658
+ id: 'ai-forever/kandinsky-2.2',
659
+ provider: 'replicate',
660
+ name: 'kandinsky-2.2',
661
+ contextWindow: 0,
662
+ tier: 'flagship',
663
+ capabilities: new Set(['chat']),
664
+ pricing: {},
665
+ metadata: {
666
+ owner: "ai-forever",
667
+ description: "multilingual text2image latent diffusion model",
668
+ runCount: 10026963,
669
+ githubUrl: "https://github.com/chenxwh/Kandinsky-2/tree/v2.2",
670
+ visibility: "public",
671
+ source: "replicate",
672
+ latestVersionId: "ad9d7879fbffa2874e1d909d1d37d9bc682889cc65b31f7bb00d2362619f194a",
673
+ cogVersion: "0.9.4"
674
+ }
675
+ }, {
676
+ id: 'fofr/sdxl-emoji',
677
+ provider: 'replicate',
678
+ name: 'sdxl-emoji',
679
+ contextWindow: 0,
680
+ tier: 'flagship',
681
+ capabilities: new Set(['image']),
682
+ pricing: {},
683
+ metadata: {
684
+ owner: "fofr",
685
+ description: "An SDXL fine-tune based on Apple Emojis",
686
+ runCount: 11077136,
687
+ githubUrl: null,
688
+ visibility: "public",
689
+ source: "replicate",
690
+ latestVersionId: "dee76b5afde21b0f01ed7925f0665b7e879c50ee718c5f78a9d38e04d523cc5e",
691
+ cogVersion: "v0.8.1+dev"
692
+ }
693
+ }, {
694
+ id: 'bytedance/sdxl-lightning-4step',
695
+ provider: 'replicate',
696
+ name: 'sdxl-lightning-4step',
697
+ contextWindow: 0,
698
+ tier: 'flagship',
699
+ capabilities: new Set(['image']),
700
+ pricing: {},
701
+ metadata: {
702
+ owner: "bytedance",
703
+ description: "SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps",
704
+ runCount: 1028178701,
705
+ githubUrl: "https://github.com/lucataco/cog-sdxl-lightning-4step",
706
+ visibility: "public",
707
+ source: "replicate",
708
+ latestVersionId: "6f7a773af6fc3e8de9d5a3c00be77c17308914bf67772726aff83496ba1e3bbe",
709
+ cogVersion: "0.14.1"
710
+ }
711
+ }, {
712
+ id: 'ideogram-ai/ideogram-v2',
713
+ provider: 'replicate',
714
+ name: 'ideogram-v2',
715
+ contextWindow: 0,
716
+ tier: 'flagship',
717
+ capabilities: new Set(['chat']),
718
+ pricing: {},
719
+ metadata: {
720
+ owner: "ideogram-ai",
721
+ description: "An excellent image model with state of the art inpainting, prompt comprehension and text rendering",
722
+ runCount: 2495426,
723
+ githubUrl: null,
724
+ visibility: "public",
725
+ source: "replicate",
726
+ latestVersionId: "6677bad7d67f0a1918c1e800ee473a83ebf68f2d5c8f7e7140d9a7e5d9d2d02d",
727
+ cogVersion: "0.16.7"
728
+ }
729
+ }, {
730
+ id: 'fofr/realvisxl-v3-multi-controlnet-lora',
731
+ provider: 'replicate',
732
+ name: 'realvisxl-v3-multi-controlnet-lora',
733
+ contextWindow: 0,
734
+ tier: 'flagship',
735
+ capabilities: new Set(['chat']),
736
+ pricing: {},
737
+ metadata: {
738
+ owner: "fofr",
739
+ description: "RealVisXl V3 with multi-controlnet, lora loading, img2img, inpainting",
740
+ runCount: 1918359,
741
+ githubUrl: "https://github.com/fofr/cog-realvisxl-3-multi-controlnet-lora",
742
+ visibility: "public",
743
+ source: "replicate",
744
+ latestVersionId: "90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade",
745
+ cogVersion: "0.8.6"
746
+ }
747
+ }, {
748
+ id: 'black-forest-labs/flux-pro',
749
+ provider: 'replicate',
750
+ name: 'flux-pro',
751
+ contextWindow: 0,
752
+ tier: 'flagship',
753
+ capabilities: new Set(['image']),
754
+ pricing: {},
755
+ metadata: {
756
+ owner: "black-forest-labs",
757
+ description: "State-of-the-art image generation with top of the line prompt following, visual quality, image detail and output diversity.",
758
+ runCount: 13331200,
759
+ githubUrl: null,
760
+ visibility: "public",
761
+ source: "replicate",
762
+ latestVersionId: "47f7ddb687b2260b914ab3d69deefa737a2d045d3b1a96dcf6ead02ea0b8576f",
763
+ cogVersion: "0.16.8"
764
+ }
765
+ }, {
766
+ id: 'tstramer/material-diffusion',
767
+ provider: 'replicate',
768
+ name: 'material-diffusion',
769
+ contextWindow: 0,
770
+ tier: 'flagship',
771
+ capabilities: new Set(['chat']),
772
+ pricing: {},
773
+ metadata: {
774
+ owner: "tstramer",
775
+ description: "Stable diffusion fork for generating tileable outputs using v1.5 model",
776
+ runCount: 2341280,
777
+ githubUrl: null,
778
+ visibility: "public",
779
+ source: "replicate",
780
+ latestVersionId: "a42692c54c0f407f803a0a8a9066160976baedb77c91171a01730f9b0d7beeff",
781
+ cogVersion: "0.4.4"
782
+ }
783
+ }, {
784
+ id: 'fermatresearch/sdxl-controlnet-lora',
785
+ provider: 'replicate',
786
+ name: 'sdxl-controlnet-lora',
787
+ contextWindow: 0,
788
+ tier: 'flagship',
789
+ capabilities: new Set(['image']),
790
+ pricing: {},
791
+ metadata: {
792
+ owner: "fermatresearch",
793
+ description: "'''Last update: Now supports img2img.''' SDXL Canny controlnet with LoRA support.",
794
+ runCount: 967998,
795
+ githubUrl: "https://github.com/BatouResearch/Cog-SDXL-ControlNet-LoRA",
796
+ visibility: "public",
797
+ source: "replicate",
798
+ latestVersionId: "3bb13fe1c33c35987b33792b01b71ed6529d03f165d1c2416375859f09ca9fef",
799
+ cogVersion: "0.8.6"
800
+ }
801
+ }, {
802
+ id: 'lucataco/realistic-vision-v5.1',
803
+ provider: 'replicate',
804
+ name: 'realistic-vision-v5.1',
805
+ contextWindow: 0,
806
+ tier: 'flagship',
807
+ capabilities: new Set(['vision']),
808
+ pricing: {},
809
+ metadata: {
810
+ owner: "lucataco",
811
+ description: "Implementation of Realistic Vision v5.1 with VAE",
812
+ runCount: 4283871,
813
+ githubUrl: "https://github.com/lucataco/cog-realistic-vision-v5.1",
814
+ visibility: "public",
815
+ source: "replicate",
816
+ latestVersionId: "2c8e954decbf70b7607a4414e5785ef9e4de4b8c51d50fb8b8b349160e0ef6bb",
817
+ cogVersion: "0.8.6"
818
+ }
819
+ }, {
820
+ id: 'stability-ai/sdxl',
821
+ provider: 'replicate',
822
+ name: 'sdxl',
823
+ contextWindow: 0,
824
+ tier: 'flagship',
825
+ capabilities: new Set(['image']),
826
+ pricing: {},
827
+ metadata: {
828
+ owner: "stability-ai",
829
+ description: "A text-to-image generative AI model that creates beautiful images",
830
+ runCount: 82487641,
831
+ githubUrl: "https://github.com/replicate/cog-sdxl",
832
+ visibility: "public",
833
+ source: "replicate",
834
+ latestVersionId: "7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
835
+ cogVersion: "0.9.5"
836
+ }
837
+ }, {
838
+ id: 'stability-ai/stable-diffusion-3.5-large',
839
+ provider: 'replicate',
840
+ name: 'stable-diffusion-3.5-large',
841
+ contextWindow: 0,
842
+ tier: 'flagship',
843
+ capabilities: new Set(['image']),
844
+ pricing: {},
845
+ metadata: {
846
+ owner: "stability-ai",
847
+ description: "A text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, thanks to Query-Key Normalization.",
848
+ runCount: 1697283,
849
+ githubUrl: null,
850
+ visibility: "public",
851
+ source: "replicate",
852
+ latestVersionId: "a82d0730394d52bae4772bf5ee7f520adab28345306c9a3737835cdda96afd3a",
853
+ cogVersion: "0.16.8"
854
+ }
855
+ }, {
856
+ id: 'black-forest-labs/flux-1.1-pro-ultra',
857
+ provider: 'replicate',
858
+ name: 'flux-1.1-pro-ultra',
859
+ contextWindow: 0,
860
+ tier: 'flagship',
861
+ capabilities: new Set(['image']),
862
+ pricing: {},
863
+ metadata: {
864
+ owner: "black-forest-labs",
865
+ description: "FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.",
866
+ runCount: 18347058,
867
+ githubUrl: null,
868
+ visibility: "public",
869
+ source: "replicate",
870
+ latestVersionId: "c6e5086a542c99e7e523a83d3017654e8618fe64ef427c772a1def05bb599f0c",
871
+ cogVersion: "0.14.3"
872
+ }
873
+ }, {
874
+ id: 'black-forest-labs/flux-1.1-pro',
875
+ provider: 'replicate',
876
+ name: 'flux-1.1-pro',
877
+ contextWindow: 0,
878
+ tier: 'flagship',
879
+ capabilities: new Set(['image']),
880
+ pricing: {},
881
+ metadata: {
882
+ owner: "black-forest-labs",
883
+ description: "Faster, better FLUX Pro. Text-to-image model with excellent image quality, prompt adherence, and output diversity.",
884
+ runCount: 62598321,
885
+ githubUrl: null,
886
+ visibility: "public",
887
+ source: "replicate",
888
+ latestVersionId: "80a09d66baa990429c2f5ae8a4306bf778a1b3775afd01cc2cc8bdbe9033769c",
889
+ cogVersion: "0.14.3"
890
+ }
891
+ }, {
892
+ id: 'stability-ai/stable-diffusion',
893
+ provider: 'replicate',
894
+ name: 'stable-diffusion',
895
+ contextWindow: 0,
896
+ tier: 'flagship',
897
+ capabilities: new Set(['image']),
898
+ pricing: {},
899
+ metadata: {
900
+ owner: "stability-ai",
901
+ description: "A latent text-to-image diffusion model capable of generating photo-realistic images given any text input",
902
+ runCount: 110770264,
903
+ githubUrl: "https://github.com/replicate/cog-stable-diffusion",
904
+ visibility: "public",
905
+ source: "replicate",
906
+ latestVersionId: "ac732df83cea7fff18b8472768c88ad041fa750ff7682a21affe81863cbe77e4",
907
+ cogVersion: "0.7.2"
908
+ }
909
+ }, {
910
+ id: 'fofr/sticker-maker',
911
+ provider: 'replicate',
912
+ name: 'sticker-maker',
913
+ contextWindow: 0,
914
+ tier: 'flagship',
915
+ capabilities: new Set(['chat']),
916
+ pricing: {},
917
+ metadata: {
918
+ owner: "fofr",
919
+ description: "Make stickers with AI. Generates graphics with transparent backgrounds.",
920
+ runCount: 1648085,
921
+ githubUrl: "https://github.com/fofr/cog-stickers",
922
+ visibility: "public",
923
+ source: "replicate",
924
+ latestVersionId: "4acb778eb059772225ec213948f0660867b2e03f277448f18cf1800b96a65a1a",
925
+ cogVersion: "0.9.5"
926
+ }
927
+ }, {
928
+ id: 'playgroundai/playground-v2.5-1024px-aesthetic',
929
+ provider: 'replicate',
930
+ name: 'playground-v2.5-1024px-aesthetic',
931
+ contextWindow: 0,
932
+ tier: 'flagship',
933
+ capabilities: new Set(['chat']),
934
+ pricing: {},
935
+ metadata: {
936
+ owner: "playgroundai",
937
+ description: "Playground v2.5 is the state-of-the-art open-source model in aesthetic quality",
938
+ runCount: 2699550,
939
+ githubUrl: "https://github.com/lucataco/cog-playground-v2.5-1024px-aesthetic",
940
+ visibility: "public",
941
+ source: "replicate",
942
+ latestVersionId: "a45f82a1382bed5c7aeb861dac7c7d191b0fdf74d8d57c4a0e6ed7d4d0bf7d24",
943
+ cogVersion: "0.9.4"
944
+ }
945
+ }, {
946
+ id: 'jagilley/controlnet-scribble',
947
+ provider: 'replicate',
948
+ name: 'controlnet-scribble',
949
+ contextWindow: 0,
950
+ tier: 'flagship',
951
+ capabilities: new Set(['chat']),
952
+ pricing: {},
953
+ metadata: {
954
+ owner: "jagilley",
955
+ description: "Generate detailed images from scribbled drawings",
956
+ runCount: 38298644,
957
+ githubUrl: "https://github.com/replicate/controlnet",
958
+ visibility: "public",
959
+ source: "replicate",
960
+ latestVersionId: "435061a1b5a4c1e26740464bf786efdfa9cb3a3ac488595a2de23e143fdb0117",
961
+ cogVersion: "0.6.1"
962
+ }
963
+ }, {
964
+ id: 'fofr/sdxl-multi-controlnet-lora',
965
+ provider: 'replicate',
966
+ name: 'sdxl-multi-controlnet-lora',
967
+ contextWindow: 0,
968
+ tier: 'flagship',
969
+ capabilities: new Set(['image']),
970
+ pricing: {},
971
+ metadata: {
972
+ owner: "fofr",
973
+ description: "Multi-controlnet, lora loading, img2img, inpainting",
974
+ runCount: 214157,
975
+ githubUrl: "https://github.com/fofr/cog-sdxl-multicontrolnet-lora",
976
+ visibility: "public",
977
+ source: "replicate",
978
+ latestVersionId: "89eb212b3d1366a83e949c12a4b45dfe6b6b313b594cb8268e864931ac9ffb16",
979
+ cogVersion: "0.8.6"
980
+ }
981
+ }, {
982
+ id: 'fofr/latent-consistency-model',
983
+ provider: 'replicate',
984
+ name: 'latent-consistency-model',
985
+ contextWindow: 0,
986
+ tier: 'flagship',
987
+ capabilities: new Set(['chat']),
988
+ pricing: {},
989
+ metadata: {
990
+ owner: "fofr",
991
+ description: "Super-fast, 0.6s per image. LCM with img2img, large batching and canny controlnet",
992
+ runCount: 1530705,
993
+ githubUrl: "https://github.com/fofr/cog-lcm",
994
+ visibility: "public",
995
+ source: "replicate",
996
+ latestVersionId: "683d19dc312f7a9f0428b04429a9ccefd28dbf7785fef083ad5cf991b65f406f",
997
+ cogVersion: "0.8.6"
998
+ }
999
+ }, {
1000
+ id: 'lucataco/dreamshaper-xl-turbo',
1001
+ provider: 'replicate',
1002
+ name: 'dreamshaper-xl-turbo',
1003
+ contextWindow: 0,
1004
+ tier: 'flagship',
1005
+ capabilities: new Set(['chat']),
1006
+ pricing: {},
1007
+ metadata: {
1008
+ owner: "lucataco",
1009
+ description: "DreamShaper is a general purpose SD model that aims at doing everything well, photos, art, anime, manga. It's designed to match Midjourney and DALL-E.",
1010
+ runCount: 225401,
1011
+ githubUrl: "https://github.com/lucataco/cog-dreamshaper-xl-turbo",
1012
+ visibility: "public",
1013
+ source: "replicate",
1014
+ latestVersionId: "0a1710e0187b01a255302738ca0158ff02a22f4638679533e111082f9dd1b615",
1015
+ cogVersion: "0.8.6"
1016
+ }
1017
+ }, {
1018
+ id: 'lucataco/open-dalle-v1.1',
1019
+ provider: 'replicate',
1020
+ name: 'open-dalle-v1.1',
1021
+ contextWindow: 0,
1022
+ tier: 'flagship',
1023
+ capabilities: new Set(['image']),
1024
+ pricing: {},
1025
+ metadata: {
1026
+ owner: "lucataco",
1027
+ description: "A unique fusion that showcases exceptional prompt adherence and semantic understanding, it seems to be a step above base SDXL and a step closer to DALLE-3 in terms of prompt comprehension",
1028
+ runCount: 131391,
1029
+ githubUrl: "https://github.com/lucataco/cog-opendalle-v1.1",
1030
+ visibility: "public",
1031
+ source: "replicate",
1032
+ latestVersionId: "1c7d4c8dec39c7306df7794b28419078cb9d18b9213ab1c21fdc46a1deca0144",
1033
+ cogVersion: "0.8.6"
1034
+ }
1035
+ }, {
1036
+ id: 'adirik/realvisxl-v3.0-turbo',
1037
+ provider: 'replicate',
1038
+ name: 'realvisxl-v3.0-turbo',
1039
+ contextWindow: 0,
1040
+ tier: 'flagship',
1041
+ capabilities: new Set(['chat']),
1042
+ pricing: {},
1043
+ metadata: {
1044
+ owner: "adirik",
1045
+ description: "Photorealism with RealVisXL V3.0 Turbo based on SDXL",
1046
+ runCount: 511520,
1047
+ githubUrl: "https://github.com/alaradirik/cog-RealVisXL",
1048
+ visibility: "public",
1049
+ source: "replicate",
1050
+ latestVersionId: "3dc73c805b11b4b01a60555e532fd3ab3f0e60d26f6584d9b8ba7e1b95858243",
1051
+ cogVersion: "0.9.0-beta10"
1052
+ }
1053
+ }, {
1054
+ id: 'datacte/proteus-v0.2',
1055
+ provider: 'replicate',
1056
+ name: 'proteus-v0.2',
1057
+ contextWindow: 0,
1058
+ tier: 'flagship',
1059
+ capabilities: new Set(['chat']),
1060
+ pricing: {},
1061
+ metadata: {
1062
+ owner: "datacte",
1063
+ description: "Proteus v0.2 shows subtle yet significant improvements over Version 0.1. It demonstrates enhanced prompt understanding that surpasses MJ6, while also approaching its stylistic capabilities.",
1064
+ runCount: 11016256,
1065
+ githubUrl: "https://github.com/lucataco/cog-proteus-v0.2",
1066
+ visibility: "public",
1067
+ source: "replicate",
1068
+ latestVersionId: "06775cd262843edbde5abab958abdbb65a0a6b58ca301c9fd78fa55c775fc019",
1069
+ cogVersion: "0.9.3"
1070
+ }
1071
+ }, {
1072
+ id: 'stability-ai/stable-diffusion-3.5-medium',
1073
+ provider: 'replicate',
1074
+ name: 'stable-diffusion-3.5-medium',
1075
+ contextWindow: 0,
1076
+ tier: 'flagship',
1077
+ capabilities: new Set(['image']),
1078
+ pricing: {},
1079
+ metadata: {
1080
+ owner: "stability-ai",
1081
+ description: "2.5 billion parameter image model with improved MMDiT-X architecture",
1082
+ runCount: 78186,
1083
+ githubUrl: null,
1084
+ visibility: "public",
1085
+ source: "replicate",
1086
+ latestVersionId: "e069811fe9b5815a6db8874c3054c15be99c8019d07ee5ad72aa63cea3cfffe3",
1087
+ cogVersion: "0.16.7"
1088
+ }
1089
+ }, {
1090
+ id: 'black-forest-labs/flux-schnell',
1091
+ provider: 'replicate',
1092
+ name: 'flux-schnell',
1093
+ contextWindow: 0,
1094
+ tier: 'flagship',
1095
+ capabilities: new Set(['image']),
1096
+ pricing: {},
1097
+ metadata: {
1098
+ owner: "black-forest-labs",
1099
+ description: "The fastest image generation model tailored for local development and personal use",
1100
+ runCount: 526559748,
1101
+ githubUrl: "https://github.com/replicate/cog-flux",
1102
+ visibility: "public",
1103
+ source: "replicate",
1104
+ latestVersionId: "c846a69991daf4c0e5d016514849d14ee5b2e6846ce6b9d6f21369e564cfe51e",
1105
+ cogVersion: "0.15.8"
1106
+ }
1107
+ }, {
1108
+ id: 'stability-ai/stable-diffusion-3.5-large-turbo',
1109
+ provider: 'replicate',
1110
+ name: 'stable-diffusion-3.5-large-turbo',
1111
+ contextWindow: 0,
1112
+ tier: 'flagship',
1113
+ capabilities: new Set(['image']),
1114
+ pricing: {},
1115
+ metadata: {
1116
+ owner: "stability-ai",
1117
+ description: "A text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, with a focus on fewer inference steps",
1118
+ runCount: 815465,
1119
+ githubUrl: null,
1120
+ visibility: "public",
1121
+ source: "replicate",
1122
+ latestVersionId: "8170d81b43c5b823dd15b0132720fdae8dadf9c46c7da484a24b8e98e6b161a2",
1123
+ cogVersion: "0.16.7"
1124
+ }
1125
+ }, {
1126
+ id: 'recraft-ai/recraft-v3',
1127
+ provider: 'replicate',
1128
+ name: 'recraft-v3',
1129
+ contextWindow: 0,
1130
+ tier: 'flagship',
1131
+ capabilities: new Set(['image']),
1132
+ pricing: {},
1133
+ metadata: {
1134
+ owner: "recraft-ai",
1135
+ description: "Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis",
1136
+ runCount: 6516404,
1137
+ githubUrl: null,
1138
+ visibility: "public",
1139
+ source: "replicate",
1140
+ latestVersionId: "a3d2a926e70e8b9b22b07feff09f47f4037cb3db1f481663513707e5b0f147fe",
1141
+ cogVersion: "0.16.8"
1142
+ }
1143
+ }, {
1144
+ id: 'recraft-ai/recraft-v3-svg',
1145
+ provider: 'replicate',
1146
+ name: 'recraft-v3-svg',
1147
+ contextWindow: 0,
1148
+ tier: 'flagship',
1149
+ capabilities: new Set(['image']),
1150
+ pricing: {},
1151
+ metadata: {
1152
+ owner: "recraft-ai",
1153
+ description: "Recraft V3 SVG (code-named red_panda) is a text-to-image model with the ability to generate high quality SVG images including logotypes, and icons. The model supports a wide list of styles.",
1154
+ runCount: 301358,
1155
+ githubUrl: null,
1156
+ visibility: "public",
1157
+ source: "replicate",
1158
+ latestVersionId: "c385df69dca5e288d8d48efd41204de66ecd1dee532a7456697e1fa0e5b9540b",
1159
+ cogVersion: "0.16.8"
1160
+ }
1161
+ }, {
1162
+ id: 'nvidia/sana',
1163
+ provider: 'replicate',
1164
+ name: 'sana',
1165
+ contextWindow: 0,
1166
+ tier: 'flagship',
1167
+ capabilities: new Set(['chat']),
1168
+ pricing: {},
1169
+ metadata: {
1170
+ owner: "nvidia",
1171
+ description: "A fast image model with wide artistic range and resolutions up to 4096x4096",
1172
+ runCount: 205678,
1173
+ githubUrl: "https://github.com/chenxwh/Sana",
1174
+ visibility: "public",
1175
+ source: "replicate",
1176
+ latestVersionId: "c6b5d2b7459910fec94432e9e1203c3cdce92d6db20f714f1355747990b52fa6",
1177
+ cogVersion: "0.13.3"
1178
+ }
1179
+ }, {
1180
+ id: 'zsxkib/blip-3',
1181
+ provider: 'replicate',
1182
+ name: 'blip-3',
1183
+ contextWindow: 0,
1184
+ tier: 'flagship',
1185
+ capabilities: new Set(['chat']),
1186
+ pricing: {},
1187
+ metadata: {
1188
+ owner: "zsxkib",
1189
+ description: "Blip 3 / XGen-MM, Answers questions about images ({blip3,xgen-mm}-phi3-mini-base-r-v1)",
1190
+ runCount: 1329181,
1191
+ githubUrl: "https://github.com/zsxkib/cog-blip-3",
1192
+ visibility: "public",
1193
+ source: "replicate",
1194
+ latestVersionId: "499bec581d8f64060fd695ec0c34d7595c6824c4118259aa8b0788e0d2d903e1",
1195
+ cogVersion: "v0.9.5+dev"
1196
+ }
1197
+ }, {
1198
+ id: 'lucataco/llama-3-vision-alpha',
1199
+ provider: 'replicate',
1200
+ name: 'llama-3-vision-alpha',
1201
+ contextWindow: 0,
1202
+ tier: 'experimental',
1203
+ capabilities: new Set(['vision', 'chat', 'streaming']),
1204
+ pricing: {},
1205
+ metadata: {
1206
+ owner: "lucataco",
1207
+ description: "Projection module trained to add vision capabilties to Llama 3 using SigLIP",
1208
+ runCount: 5789,
1209
+ githubUrl: "https://github.com/lucataco/cog-llama-3-vision-alpha",
1210
+ visibility: "public",
1211
+ source: "replicate",
1212
+ latestVersionId: "79f9f3418f65fb5d180978a969d5646e33f8ca67430a2fe903c9a4be82565925",
1213
+ cogVersion: "0.12.0"
1214
+ }
1215
+ }, {
1216
+ id: 'lucataco/moondream2',
1217
+ provider: 'replicate',
1218
+ name: 'moondream2',
1219
+ contextWindow: 0,
1220
+ tier: 'flagship',
1221
+ capabilities: new Set(['chat', 'streaming']),
1222
+ pricing: {},
1223
+ metadata: {
1224
+ owner: "lucataco",
1225
+ description: "moondream2 is a small vision language model designed to run efficiently on edge devices",
1226
+ runCount: 4474833,
1227
+ githubUrl: "https://github.com/lucataco/cog-moondream2",
1228
+ visibility: "public",
1229
+ source: "replicate",
1230
+ latestVersionId: "72ccb656353c348c1385df54b237eeb7bfa874bf11486cf0b9473e691b662d31",
1231
+ cogVersion: "0.9.13"
1232
+ }
1233
+ }, {
1234
+ id: 'lucataco/smolvlm-instruct',
1235
+ provider: 'replicate',
1236
+ name: 'smolvlm-instruct',
1237
+ contextWindow: 0,
1238
+ tier: 'flagship',
1239
+ capabilities: new Set(['chat']),
1240
+ pricing: {},
1241
+ metadata: {
1242
+ owner: "lucataco",
1243
+ description: "SmolVLM-Instruct by HuggingFaceTB",
1244
+ runCount: 3298,
1245
+ githubUrl: "https://github.com/lucataco/cog-smolvlm-instruct",
1246
+ visibility: "public",
1247
+ source: "replicate",
1248
+ latestVersionId: "e79f1e0eb64fe9a145d0a0afd6127d43b37de66eaaa2e00ff3d165bc14097dfb",
1249
+ cogVersion: "0.13.3"
1250
+ }
1251
+ }, {
1252
+ id: 'lucataco/fuyu-8b',
1253
+ provider: 'replicate',
1254
+ name: 'fuyu-8b',
1255
+ contextWindow: 0,
1256
+ tier: 'flagship',
1257
+ capabilities: new Set(['chat']),
1258
+ pricing: {},
1259
+ metadata: {
1260
+ owner: "lucataco",
1261
+ description: "Fuyu-8B is a multi-modal text and image transformer trained by Adept AI",
1262
+ runCount: 4607,
1263
+ githubUrl: "https://github.com/lucataco/cog-fuyu",
1264
+ visibility: "public",
1265
+ source: "replicate",
1266
+ latestVersionId: "42f23bc876570a46f5a90737086fbc4c3f79dd11753a28eaa39544dd391815e9",
1267
+ cogVersion: "0.8.6"
1268
+ }
1269
+ }, {
1270
+ id: 'lucataco/qwen-vl-chat',
1271
+ provider: 'replicate',
1272
+ name: 'qwen-vl-chat',
1273
+ contextWindow: 0,
1274
+ tier: 'flagship',
1275
+ capabilities: new Set(['chat', 'streaming']),
1276
+ pricing: {},
1277
+ metadata: {
1278
+ owner: "lucataco",
1279
+ description: "A multimodal LLM-based AI assistant, which is trained with alignment techniques. Qwen-VL-Chat supports more flexible interaction, such as multi-round question answering, and creative capabilities.",
1280
+ runCount: 825540,
1281
+ githubUrl: "https://github.com/lucataco/cog-qwen-vl-chat",
1282
+ visibility: "public",
1283
+ source: "replicate",
1284
+ latestVersionId: "50881b153b4d5f72b3db697e2bbad23bb1277ab741c5b52d80cd6ee17ea660e9",
1285
+ cogVersion: "0.8.6"
1286
+ }
1287
+ }, {
1288
+ id: 'lucataco/qwen2-vl-7b-instruct',
1289
+ provider: 'replicate',
1290
+ name: 'qwen2-vl-7b-instruct',
1291
+ contextWindow: 0,
1292
+ tier: 'flagship',
1293
+ capabilities: new Set(['chat']),
1294
+ pricing: {},
1295
+ metadata: {
1296
+ owner: "lucataco",
1297
+ description: "Latest model in the Qwen family for chatting with video and image models",
1298
+ runCount: 260729,
1299
+ githubUrl: "https://github.com/lucataco/cog-qwen2-vl-7b-instruct",
1300
+ visibility: "public",
1301
+ source: "replicate",
1302
+ latestVersionId: "bf57361c75677fc33d480d0c5f02926e621b2caa2000347cb74aeae9d2ca07ee",
1303
+ cogVersion: "0.13.6"
1304
+ }
1305
+ }, {
1306
+ id: 'lucataco/sdxl-clip-interrogator',
1307
+ provider: 'replicate',
1308
+ name: 'sdxl-clip-interrogator',
1309
+ contextWindow: 0,
1310
+ tier: 'flagship',
1311
+ capabilities: new Set(['image']),
1312
+ pricing: {},
1313
+ metadata: {
1314
+ owner: "lucataco",
1315
+ description: "CLIP Interrogator for SDXL optimizes text prompts to match a given image",
1316
+ runCount: 848611,
1317
+ githubUrl: "https://github.com/lucataco/cog-sdxl-clip-interrogator",
1318
+ visibility: "public",
1319
+ source: "replicate",
1320
+ latestVersionId: "b8dd624ad312d215250b362af0ecff05d7ad4f8270f9beb034c483d70682e7b3",
1321
+ cogVersion: "0.9.6"
1322
+ }
1323
+ }, {
1324
+ id: 'zsxkib/idefics3',
1325
+ provider: 'replicate',
1326
+ name: 'idefics3',
1327
+ contextWindow: 0,
1328
+ tier: 'flagship',
1329
+ capabilities: new Set(['chat']),
1330
+ pricing: {},
1331
+ metadata: {
1332
+ owner: "zsxkib",
1333
+ description: "Idefics3-8B-Llama3, Answers questions and caption about images",
1334
+ runCount: 2476,
1335
+ githubUrl: null,
1336
+ visibility: "public",
1337
+ source: "replicate",
1338
+ latestVersionId: "b06f5f6b6249b27d0b00d1b794240e5641190d1582ad68c40ef53778459bb593",
1339
+ cogVersion: "0.9.14"
1340
+ }
1341
+ }, {
1342
+ id: 'lucataco/ollama-llama3.2-vision-90b',
1343
+ provider: 'replicate',
1344
+ name: 'ollama-llama3.2-vision-90b',
1345
+ contextWindow: 0,
1346
+ tier: 'flagship',
1347
+ capabilities: new Set(['vision', 'chat', 'streaming']),
1348
+ pricing: {},
1349
+ metadata: {
1350
+ owner: "lucataco",
1351
+ description: "Ollama Llama 3.2 Vision 90B",
1352
+ runCount: 3417,
1353
+ githubUrl: "https://github.com/lucataco/cog-ollama-llama3.2-vision-90b",
1354
+ visibility: "public",
1355
+ source: "replicate",
1356
+ latestVersionId: "54202b223d5351c5afe5c0c9dba2b3042293b839d022e76f53d66ab30b9dc814",
1357
+ cogVersion: "0.13.6"
1358
+ }
1359
+ }, {
1360
+ id: 'lucataco/ollama-llama3.2-vision-11b',
1361
+ provider: 'replicate',
1362
+ name: 'ollama-llama3.2-vision-11b',
1363
+ contextWindow: 0,
1364
+ tier: 'flagship',
1365
+ capabilities: new Set(['vision', 'chat', 'streaming']),
1366
+ pricing: {},
1367
+ metadata: {
1368
+ owner: "lucataco",
1369
+ description: "Ollama Llama 3.2 Vision 11B",
1370
+ runCount: 2712,
1371
+ githubUrl: "https://github.com/lucataco/cog-ollama-llama3.2-vision-90b",
1372
+ visibility: "public",
1373
+ source: "replicate",
1374
+ latestVersionId: "d4e81fc1472556464f1ee5cea4de177b2fe95a6eaadb5f63335df1ba654597af",
1375
+ cogVersion: "0.13.6"
1376
+ }
1377
+ }, {
1378
+ id: 'lucataco/florence-2-base',
1379
+ provider: 'replicate',
1380
+ name: 'florence-2-base',
1381
+ contextWindow: 0,
1382
+ tier: 'flagship',
1383
+ capabilities: new Set(['chat']),
1384
+ pricing: {},
1385
+ metadata: {
1386
+ owner: "lucataco",
1387
+ description: "Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks",
1388
+ runCount: 125407,
1389
+ githubUrl: "https://github.com/lucataco/cog-florence-2-base",
1390
+ visibility: "public",
1391
+ source: "replicate",
1392
+ latestVersionId: "c81609117f666d3a86b262447f80d41ac5158a76adb56893301843a23165eaf8",
1393
+ cogVersion: "0.9.9"
1394
+ }
1395
+ }, {
1396
+ id: 'yorickvp/llava-13b',
1397
+ provider: 'replicate',
1398
+ name: 'llava-13b',
1399
+ contextWindow: 0,
1400
+ tier: 'flagship',
1401
+ capabilities: new Set(['chat']),
1402
+ pricing: {},
1403
+ metadata: {
1404
+ owner: "yorickvp",
1405
+ description: "Visual instruction tuning towards large language and vision models with GPT-4 level capabilities",
1406
+ runCount: 31772668,
1407
+ githubUrl: "https://github.com/haotian-liu/LLaVA",
1408
+ visibility: "public",
1409
+ source: "replicate",
1410
+ latestVersionId: "80537f9eead1a5bfa72d5ac6ea6414379be41d4d4f6679fd776e9535d1eb58bb",
1411
+ cogVersion: "0.9.5"
1412
+ }
1413
+ }, {
1414
+ id: 'zsxkib/molmo-7b',
1415
+ provider: 'replicate',
1416
+ name: 'molmo-7b',
1417
+ contextWindow: 0,
1418
+ tier: 'flagship',
1419
+ capabilities: new Set(['chat']),
1420
+ pricing: {},
1421
+ metadata: {
1422
+ owner: "zsxkib",
1423
+ description: "allenai/Molmo-7B-D-0924, Answers questions and caption about images",
1424
+ runCount: 595150,
1425
+ githubUrl: "https://github.com/zsxkib/cog-molmo-7b-d",
1426
+ visibility: "public",
1427
+ source: "replicate",
1428
+ latestVersionId: "76ebd700864218a4ca97ac1ccff068be7222272859f9ea2ae1dd4ac073fa8de8",
1429
+ cogVersion: "0.9.24"
1430
+ }
1431
+ }, {
1432
+ id: 'salesforce/blip',
1433
+ provider: 'replicate',
1434
+ name: 'blip',
1435
+ contextWindow: 0,
1436
+ tier: 'flagship',
1437
+ capabilities: new Set(['chat']),
1438
+ pricing: {},
1439
+ metadata: {
1440
+ owner: "salesforce",
1441
+ description: "Generate image captions",
1442
+ runCount: 168531263,
1443
+ githubUrl: "https://github.com/salesforce/BLIP",
1444
+ visibility: "public",
1445
+ source: "replicate",
1446
+ latestVersionId: "2e1dddc8621f72155f24cf2e0adbde548458d3cab9f00c0139eea840d0ac4746",
1447
+ cogVersion: "0.4.1"
1448
+ }
1449
+ }, {
1450
+ id: 'joehoover/mplug-owl',
1451
+ provider: 'replicate',
1452
+ name: 'mplug-owl',
1453
+ contextWindow: 0,
1454
+ tier: 'flagship',
1455
+ capabilities: new Set(['chat', 'streaming']),
1456
+ pricing: {},
1457
+ metadata: {
1458
+ owner: "joehoover",
1459
+ description: "An instruction-tuned multimodal large language model that generates text based on user-provided prompts and images",
1460
+ runCount: 55800,
1461
+ githubUrl: "https://github.com/replicate/cog-mplug-owl",
1462
+ visibility: "public",
1463
+ source: "replicate"
1464
+ }
1465
+ }, {
1466
+ id: 'j-min/clip-caption-reward',
1467
+ provider: 'replicate',
1468
+ name: 'clip-caption-reward',
1469
+ contextWindow: 0,
1470
+ tier: 'flagship',
1471
+ capabilities: new Set(['chat']),
1472
+ pricing: {},
1473
+ metadata: {
1474
+ owner: "j-min",
1475
+ description: "Fine-grained Image Captioning with CLIP Reward",
1476
+ runCount: 296124,
1477
+ githubUrl: "https://github.com/j-min/CLIP-Caption-Reward",
1478
+ visibility: "public",
1479
+ source: "replicate",
1480
+ latestVersionId: "de37751f75135f7ebbe62548e27d6740d5155dfefdf6447db35c9865253d7e06",
1481
+ cogVersion: "0.3.4"
1482
+ }
1483
+ }, {
1484
+ id: 'nohamoamary/image-captioning-with-visual-attention',
1485
+ provider: 'replicate',
1486
+ name: 'image-captioning-with-visual-attention',
1487
+ contextWindow: 0,
1488
+ tier: 'flagship',
1489
+ capabilities: new Set(['chat']),
1490
+ pricing: {},
1491
+ metadata: {
1492
+ owner: "nohamoamary",
1493
+ description: "datasets: Flickr8k",
1494
+ runCount: 11281,
1495
+ githubUrl: "https://github.com/NohaMoAmary/image-captioning-with-visual-attention.git",
1496
+ visibility: "public",
1497
+ source: "replicate",
1498
+ latestVersionId: "9bb60a6baa58801aa7cd4c4fafc95fcf1531bf59b84962aff5a718f4d1f58986",
1499
+ cogVersion: "0.6.1"
1500
+ }
1501
+ }, {
1502
+ id: 'pharmapsychotic/clip-interrogator',
1503
+ provider: 'replicate',
1504
+ name: 'clip-interrogator',
1505
+ contextWindow: 0,
1506
+ tier: 'flagship',
1507
+ capabilities: new Set(['image']),
1508
+ pricing: {},
1509
+ metadata: {
1510
+ owner: "pharmapsychotic",
1511
+ description: "The CLIP Interrogator is a prompt engineering tool that combines OpenAI's CLIP and Salesforce's BLIP to optimize text prompts to match a given image. Use the resulting prompts with text-to-image models like Stable Diffusion to create cool art!",
1512
+ runCount: 4561943,
1513
+ githubUrl: "https://github.com/pharmapsychotic/clip-interrogator",
1514
+ visibility: "public",
1515
+ source: "replicate",
1516
+ latestVersionId: "8151e1c9f47e696fa316146a2e35812ccf79cfc9eba05b11c7f450155102af70",
1517
+ cogVersion: "0.8.6"
1518
+ }
1519
+ }, {
1520
+ id: 'rmokady/clip_prefix_caption',
1521
+ provider: 'replicate',
1522
+ name: 'clip_prefix_caption',
1523
+ contextWindow: 0,
1524
+ tier: 'flagship',
1525
+ capabilities: new Set(['chat']),
1526
+ pricing: {},
1527
+ metadata: {
1528
+ owner: "rmokady",
1529
+ description: "Simple image captioning model using CLIP and GPT-2",
1530
+ runCount: 1733560,
1531
+ githubUrl: "https://github.com/rmokady/CLIP_prefix_caption",
1532
+ visibility: "public",
1533
+ source: "replicate",
1534
+ latestVersionId: "9a34a6339872a03f45236f114321fb51fc7aa8269d38ae0ce5334969981e4cd8",
1535
+ cogVersion: "0.4.1"
1536
+ }
1537
+ }, {
1538
+ id: 'methexis-inc/img2prompt',
1539
+ provider: 'replicate',
1540
+ name: 'img2prompt',
1541
+ contextWindow: 0,
1542
+ tier: 'flagship',
1543
+ capabilities: new Set(['chat']),
1544
+ pricing: {},
1545
+ metadata: {
1546
+ owner: "methexis-inc",
1547
+ description: "Get an approximate text prompt, with style, matching an image. (Optimized for stable-diffusion (clip ViT-L/14))",
1548
+ runCount: 2654996,
1549
+ githubUrl: "https://github.com/pharmapsychotic/clip-interrogator",
1550
+ visibility: "public",
1551
+ source: "replicate",
1552
+ latestVersionId: "50adaf2d3ad20a6f911a8a9e3ccf777b263b8596fbd2c8fc26e8888f8a0edbb5",
1553
+ cogVersion: "0.4.1"
1554
+ }
1555
+ }, {
1556
+ id: 'andreasjansson/blip-2',
1557
+ provider: 'replicate',
1558
+ name: 'blip-2',
1559
+ contextWindow: 0,
1560
+ tier: 'flagship',
1561
+ capabilities: new Set(['chat']),
1562
+ pricing: {},
1563
+ metadata: {
1564
+ owner: "andreasjansson",
1565
+ description: "Answers questions about images",
1566
+ runCount: 30891261,
1567
+ githubUrl: "https://github.com/daanelson/cog-blip-2",
1568
+ visibility: "public",
1569
+ source: "replicate",
1570
+ latestVersionId: "f677695e5e89f8b236e52ecd1d3f01beb44c34606419bcc19345e046d8f786f9",
1571
+ cogVersion: "0.8.3"
1572
+ }
1573
+ }, {
1574
+ id: 'daanelson/minigpt-4',
1575
+ provider: 'replicate',
1576
+ name: 'minigpt-4',
1577
+ contextWindow: 0,
1578
+ tier: 'efficient',
1579
+ capabilities: new Set(['chat', 'streaming']),
1580
+ pricing: {},
1581
+ metadata: {
1582
+ owner: "daanelson",
1583
+ description: "A model which generates text in response to an input image and prompt.",
1584
+ runCount: 1841882,
1585
+ githubUrl: "https://github.com/daanelson/MiniGPT-4",
1586
+ visibility: "public",
1587
+ source: "replicate",
1588
+ latestVersionId: "e447a8583cffd86ce3b93f9c2cd24f2eae603d99ace6afa94b33a08e94a3cd06",
1589
+ cogVersion: "v0.7.0-beta17+dev"
1590
+ }
1591
+ }, {
1592
+ id: 'joehoover/instructblip-vicuna13b',
1593
+ provider: 'replicate',
1594
+ name: 'instructblip-vicuna13b',
1595
+ contextWindow: 0,
1596
+ tier: 'flagship',
1597
+ capabilities: new Set(['chat', 'streaming']),
1598
+ pricing: {},
1599
+ metadata: {
1600
+ owner: "joehoover",
1601
+ description: "An instruction-tuned multi-modal model based on BLIP-2 and Vicuna-13B",
1602
+ runCount: 257514,
1603
+ githubUrl: "https://github.com/replicate/cog-lavis",
1604
+ visibility: "public",
1605
+ source: "replicate"
1606
+ }
1607
+ }, {
1608
+ id: 'zsxkib/uform-gen',
1609
+ provider: 'replicate',
1610
+ name: 'uform-gen',
1611
+ contextWindow: 0,
1612
+ tier: 'flagship',
1613
+ capabilities: new Set(['chat']),
1614
+ pricing: {},
1615
+ metadata: {
1616
+ owner: "zsxkib",
1617
+ description: "🖼️ Super fast 1.5B Image Captioning/VQA Multimodal LLM (Image-to-Text) 🖋️",
1618
+ runCount: 2342,
1619
+ githubUrl: "https://github.com/zsxkib/cog-uform-gen",
1620
+ visibility: "public",
1621
+ source: "replicate",
1622
+ latestVersionId: "e6fa8e2d076907b45a0b535a14ddb22402548c2e478310cd18daa1c4c01f422b",
1623
+ cogVersion: "0.8.6"
1624
+ }
1625
+ }, {
1626
+ id: 'fofr/deprecated-batch-image-captioning',
1627
+ provider: 'replicate',
1628
+ name: 'deprecated-batch-image-captioning',
1629
+ contextWindow: 0,
1630
+ tier: 'flagship',
1631
+ capabilities: new Set(['chat']),
1632
+ pricing: {},
1633
+ metadata: {
1634
+ owner: "fofr",
1635
+ description: "A wrapper model for captioning multiple images using GPT, Claude or Gemini, useful for lora training",
1636
+ runCount: 1541,
1637
+ githubUrl: "https://github.com/fofr/cog-batch-image-captioning",
1638
+ visibility: "public",
1639
+ source: "replicate",
1640
+ latestVersionId: "d0adb15f4826881a68f1d82e0b10fe2ee1af536632dc8313f7f777ed8d264726",
1641
+ cogVersion: "0.9.14"
1642
+ }
1643
+ }, {
1644
+ id: 'minimax/speech-02-hd',
1645
+ provider: 'replicate',
1646
+ name: 'speech-02-hd',
1647
+ contextWindow: 0,
1648
+ tier: 'flagship',
1649
+ capabilities: new Set(['audio']),
1650
+ pricing: {},
1651
+ metadata: {
1652
+ owner: "minimax",
1653
+ description: "Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Optimized for high-fidelity applications like voiceovers and audiobooks.",
1654
+ runCount: 904750,
1655
+ githubUrl: null,
1656
+ visibility: "public",
1657
+ source: "replicate",
1658
+ latestVersionId: "29657f664032844b8f800486164cf26acb2507288e348133e78ae871a43211d0",
1659
+ cogVersion: "0.14.7"
1660
+ }
1661
+ }, {
1662
+ id: 'minimax/voice-cloning',
1663
+ provider: 'replicate',
1664
+ name: 'voice-cloning',
1665
+ contextWindow: 0,
1666
+ tier: 'flagship',
1667
+ capabilities: new Set(['audio']),
1668
+ pricing: {},
1669
+ metadata: {
1670
+ owner: "minimax",
1671
+ description: "Clone voices to use with Minimax's speech-02-hd and speech-02-turbo",
1672
+ runCount: 17733,
1673
+ githubUrl: null,
1674
+ visibility: "public",
1675
+ source: "replicate",
1676
+ latestVersionId: "aa25ee1296b5c036b003ef80d32c83983c522e8c7d6f108460bbb0af97ebe93a",
1677
+ cogVersion: "0.14.7"
1678
+ }
1679
+ }, {
1680
+ id: 'resemble-ai/chatterbox-pro',
1681
+ provider: 'replicate',
1682
+ name: 'chatterbox-pro',
1683
+ contextWindow: 0,
1684
+ tier: 'flagship',
1685
+ capabilities: new Set(['chat', 'streaming']),
1686
+ pricing: {},
1687
+ metadata: {
1688
+ owner: "resemble-ai",
1689
+ description: "Generate expressive, natural speech with Resemble AI's Chatterbox.",
1690
+ runCount: 14419,
1691
+ githubUrl: null,
1692
+ visibility: "public",
1693
+ source: "replicate",
1694
+ latestVersionId: "301e12652e84fbba1524e5f2758a9a92c6bd205792304f53c057b7f9ab091342",
1695
+ cogVersion: "0.15.5"
1696
+ }
1697
+ }, {
1698
+ id: 'chenxwh/openvoice',
1699
+ provider: 'replicate',
1700
+ name: 'openvoice',
1701
+ contextWindow: 0,
1702
+ tier: 'flagship',
1703
+ capabilities: new Set(['audio']),
1704
+ pricing: {},
1705
+ metadata: {
1706
+ owner: "chenxwh",
1707
+ description: "Updated to OpenVoice v2: Versatile Instant Voice Cloning",
1708
+ runCount: 77597,
1709
+ githubUrl: "https://github.com/chenxwh/OpenVoice",
1710
+ visibility: "public",
1711
+ source: "replicate",
1712
+ latestVersionId: "d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d",
1713
+ cogVersion: "v0.9.6+dev"
1714
+ }
1715
+ }, {
1716
+ id: 'fermatresearch/spanish-f5-tts',
1717
+ provider: 'replicate',
1718
+ name: 'spanish-f5-tts',
1719
+ contextWindow: 0,
1720
+ tier: 'flagship',
1721
+ capabilities: new Set(['audio']),
1722
+ pricing: {},
1723
+ metadata: {
1724
+ owner: "fermatresearch",
1725
+ description: "A F5-TTS fine-tuned for Spanish",
1726
+ runCount: 918,
1727
+ githubUrl: null,
1728
+ visibility: "public",
1729
+ source: "replicate",
1730
+ latestVersionId: "f26405b801a0b0945679fb3adf9bbca7ab8559c7fd9cf7cd2a68067c3aab83f7",
1731
+ cogVersion: "0.11.6"
1732
+ }
1733
+ }, {
1734
+ id: 'x-lance/f5-tts',
1735
+ provider: 'replicate',
1736
+ name: 'f5-tts',
1737
+ contextWindow: 0,
1738
+ tier: 'flagship',
1739
+ capabilities: new Set(['audio']),
1740
+ pricing: {},
1741
+ metadata: {
1742
+ owner: "x-lance",
1743
+ description: "F5-TTS, the new state-of-the-art in open source voice cloning",
1744
+ runCount: 32024,
1745
+ githubUrl: "https://github.com/cuuupid/cog-f5-tts",
1746
+ visibility: "public",
1747
+ source: "replicate",
1748
+ latestVersionId: "87faf6dd7a692dd82043f662e76369cab126a2cf1937e25a9d41e0b834fd230e",
1749
+ cogVersion: "0.9.20"
1750
+ }
1751
+ }, {
1752
+ id: 'platform-kit/mars5-tts',
1753
+ provider: 'replicate',
1754
+ name: 'mars5-tts',
1755
+ contextWindow: 0,
1756
+ tier: 'flagship',
1757
+ capabilities: new Set(['audio']),
1758
+ pricing: {},
1759
+ metadata: {
1760
+ owner: "platform-kit",
1761
+ description: "A novel speech model for insane prosody.",
1762
+ runCount: 517,
1763
+ githubUrl: "https://github.com/Camb-ai/MARS5-TTS",
1764
+ visibility: "public",
1765
+ source: "replicate",
1766
+ latestVersionId: "6aed0f11f3ba7b13d59ab3228355e7b1ea943479673cc57e10e99ba766536811",
1767
+ cogVersion: "0.8.6"
1768
+ }
1769
+ }, {
1770
+ id: 'lucataco/pheme',
1771
+ provider: 'replicate',
1772
+ name: 'pheme',
1773
+ contextWindow: 0,
1774
+ tier: 'flagship',
1775
+ capabilities: new Set(['chat', 'streaming']),
1776
+ pricing: {},
1777
+ metadata: {
1778
+ owner: "lucataco",
1779
+ description: "Pheme generates a variety of conversational voices in 16 kHz for phone-call applications",
1780
+ runCount: 557,
1781
+ githubUrl: "https://github.com/lucataco/pheme",
1782
+ visibility: "public",
1783
+ source: "replicate",
1784
+ latestVersionId: "f307b9d2b9966608aec791d4a741dc3806f95d9eb92300fdcefeb9aecd4594cd",
1785
+ cogVersion: "0.8.6"
1786
+ }
1787
+ }, {
1788
+ id: 'awerks/neon-tts',
1789
+ provider: 'replicate',
1790
+ name: 'neon-tts',
1791
+ contextWindow: 0,
1792
+ tier: 'flagship',
1793
+ capabilities: new Set(['audio']),
1794
+ pricing: {},
1795
+ metadata: {
1796
+ owner: "awerks",
1797
+ description: "NeonAI Coqui AI TTS Plugin.",
1798
+ runCount: 160815,
1799
+ githubUrl: "https://github.com/NeonGeckoCom/neon-tts-plugin-coqui",
1800
+ visibility: "public",
1801
+ source: "replicate",
1802
+ latestVersionId: "139606fe1536f85a9f07d87982400b8140c9a9673733d47913af96738894128f",
1803
+ cogVersion: "0.8.3"
1804
+ }
1805
+ }, {
1806
+ id: 'cjwbw/parler-tts',
1807
+ provider: 'replicate',
1808
+ name: 'parler-tts',
1809
+ contextWindow: 0,
1810
+ tier: 'flagship',
1811
+ capabilities: new Set(['audio']),
1812
+ pricing: {},
1813
+ metadata: {
1814
+ owner: "cjwbw",
1815
+ description: "lightweight text-to-speech (TTS) model, trained on 10.5K hours of audio data",
1816
+ runCount: 2656,
1817
+ githubUrl: "https://github.com/huggingface/parler-tts",
1818
+ visibility: "public",
1819
+ source: "replicate",
1820
+ latestVersionId: "bf38249a8cc143b97b5108570d1c81b8321881dd91fe7837877e7dfa3a0fad27",
1821
+ cogVersion: "0.9.4"
1822
+ }
1823
+ }, {
1824
+ id: 'cjwbw/voicecraft',
1825
+ provider: 'replicate',
1826
+ name: 'voicecraft',
1827
+ contextWindow: 0,
1828
+ tier: 'flagship',
1829
+ capabilities: new Set(['audio']),
1830
+ pricing: {},
1831
+ metadata: {
1832
+ owner: "cjwbw",
1833
+ description: "Zero-Shot Speech Editing and Text-to-Speech in the Wild",
1834
+ runCount: 10613,
1835
+ githubUrl: "https://github.com/jasonppy/VoiceCraft",
1836
+ visibility: "public",
1837
+ source: "replicate",
1838
+ latestVersionId: "db97f6312d4c4d20e500e47fd95d8f14b00d8d28e046834faffb7999d83b6b30",
1839
+ cogVersion: "0.13.7"
1840
+ }
1841
+ }, {
1842
+ id: 'camenduru/metavoice',
1843
+ provider: 'replicate',
1844
+ name: 'metavoice',
1845
+ contextWindow: 0,
1846
+ tier: 'flagship',
1847
+ capabilities: new Set(['audio']),
1848
+ pricing: {},
1849
+ metadata: {
1850
+ owner: "camenduru",
1851
+ description: "MetaVoice-1B: 1.2B parameter base model trained on 100K hours of speech",
1852
+ runCount: 13446,
1853
+ githubUrl: "https://github.com/camenduru/metavoice-replicate",
1854
+ visibility: "public",
1855
+ source: "replicate",
1856
+ latestVersionId: "713109ece68b60131018e86585221826650aba6d11ffd4e314f50c7598014358",
1857
+ cogVersion: "0.9.0-beta11"
1858
+ }
1859
+ }, {
1860
+ id: 'zsxkib/dia',
1861
+ provider: 'replicate',
1862
+ name: 'dia',
1863
+ contextWindow: 0,
1864
+ tier: 'flagship',
1865
+ capabilities: new Set(['chat']),
1866
+ pricing: {},
1867
+ metadata: {
1868
+ owner: "zsxkib",
1869
+ description: "Dia 1.6B by Nari Labs, Generates realistic dialogue audio from text, including non-verbal cues and voice cloning",
1870
+ runCount: 9345,
1871
+ githubUrl: "https://github.com/zsxkib/cog-dia",
1872
+ visibility: "public",
1873
+ source: "replicate",
1874
+ latestVersionId: "2119e338ca5c0dacd3def83158d6c80d431f2ac1024146d8cca9220b74385599",
1875
+ cogVersion: "0.15.10"
1876
+ }
1877
+ }, {
1878
+ id: 'adirik/styletts2',
1879
+ provider: 'replicate',
1880
+ name: 'styletts2',
1881
+ contextWindow: 0,
1882
+ tier: 'flagship',
1883
+ capabilities: new Set(['audio']),
1884
+ pricing: {},
1885
+ metadata: {
1886
+ owner: "adirik",
1887
+ description: "Generates speech from text",
1888
+ runCount: 131829,
1889
+ githubUrl: "https://github.com/yl4579/StyleTTS2",
1890
+ visibility: "public",
1891
+ source: "replicate",
1892
+ latestVersionId: "989cb5ea6d2401314eb30685740cb9f6fd1c9001b8940659b406f952837ab5ac",
1893
+ cogVersion: "0.9.0-beta10"
1894
+ }
1895
+ }, {
1896
+ id: 'minimax/speech-02-turbo',
1897
+ provider: 'replicate',
1898
+ name: 'speech-02-turbo',
1899
+ contextWindow: 0,
1900
+ tier: 'flagship',
1901
+ capabilities: new Set(['audio']),
1902
+ pricing: {},
1903
+ metadata: {
1904
+ owner: "minimax",
1905
+ description: "Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Designed for real-time applications with low latency",
1906
+ runCount: 4642039,
1907
+ githubUrl: null,
1908
+ visibility: "public",
1909
+ source: "replicate",
1910
+ latestVersionId: "43b17801b02267d0baf70071ff440358f75499f20ad5c51118a2fdad14ba9b8c",
1911
+ cogVersion: "0.14.7"
1912
+ }
1913
+ }, {
1914
+ id: 'jaaari/kokoro-82m',
1915
+ provider: 'replicate',
1916
+ name: 'kokoro-82m',
1917
+ contextWindow: 0,
1918
+ tier: 'flagship',
1919
+ capabilities: new Set(['audio']),
1920
+ pricing: {},
1921
+ metadata: {
1922
+ owner: "jaaari",
1923
+ description: "Kokoro v1.0 - text-to-speech (82M params, based on StyleTTS2)",
1924
+ runCount: 53602127,
1925
+ githubUrl: "https://github.com/hexgrad/kokoro",
1926
+ visibility: "public",
1927
+ source: "replicate",
1928
+ latestVersionId: "f559560eb822dc509045f3921a1921234918b91739db4bf3daab2169b71c7a13",
1929
+ cogVersion: "0.13.6"
1930
+ }
1931
+ }, {
1932
+ id: 'resemble-ai/chatterbox-multilingual',
1933
+ provider: 'replicate',
1934
+ name: 'chatterbox-multilingual',
1935
+ contextWindow: 0,
1936
+ tier: 'flagship',
1937
+ capabilities: new Set(['chat', 'streaming']),
1938
+ pricing: {},
1939
+ metadata: {
1940
+ owner: "resemble-ai",
1941
+ description: "Generate expressive, natural speech in 23 languages. Features instant voice cloning from short audio, emotion control, and seamless cross-language voice transfer.",
1942
+ runCount: 2618,
1943
+ githubUrl: "https://github.com/zsxkib/cog-ResembleAI-Chatterbox-Multilingual-TTS",
1944
+ visibility: "public",
1945
+ source: "replicate",
1946
+ latestVersionId: "9cfba4c265e685f840612be835424f8c33bdee685d7466ece7684b0d9d4c0b1c",
1947
+ cogVersion: "0.16.2"
1948
+ }
1949
+ }, {
1950
+ id: 'lucataco/csm-1b',
1951
+ provider: 'replicate',
1952
+ name: 'csm-1b',
1953
+ contextWindow: 0,
1954
+ tier: 'flagship',
1955
+ capabilities: new Set(['chat', 'streaming']),
1956
+ pricing: {},
1957
+ metadata: {
1958
+ owner: "lucataco",
1959
+ description: "CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs",
1960
+ runCount: 961,
1961
+ githubUrl: "https://github.com/lucataco/cog-csm",
1962
+ visibility: "public",
1963
+ source: "replicate",
1964
+ latestVersionId: "3e59b10a9894c54ae5f2fc0347e3a2f5c82f0574407e53a7d9f76ec7c502ad03",
1965
+ cogVersion: "0.14.2"
1966
+ }
1967
+ }, {
1968
+ id: 'lucataco/orpheus-3b-0.1-ft',
1969
+ provider: 'replicate',
1970
+ name: 'orpheus-3b-0.1-ft',
1971
+ contextWindow: 0,
1972
+ tier: 'flagship',
1973
+ capabilities: new Set(['chat']),
1974
+ pricing: {},
1975
+ metadata: {
1976
+ owner: "lucataco",
1977
+ description: "Orpheus 3B - high quality, emotive Text to Speech",
1978
+ runCount: 29914,
1979
+ githubUrl: "https://github.com/lucataco/cog-orpheus-3b-0.1-ft",
1980
+ visibility: "public",
1981
+ source: "replicate",
1982
+ latestVersionId: "79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f",
1983
+ cogVersion: "0.14.2"
1984
+ }
1985
+ }, {
1986
+ id: 'resemble-ai/chatterbox',
1987
+ provider: 'replicate',
1988
+ name: 'chatterbox',
1989
+ contextWindow: 0,
1990
+ tier: 'flagship',
1991
+ capabilities: new Set(['chat', 'streaming']),
1992
+ pricing: {},
1993
+ metadata: {
1994
+ owner: "resemble-ai",
1995
+ description: "Generate expressive, natural speech. Features unique emotion control, instant voice cloning from short audio, and built-in watermarking.",
1996
+ runCount: 134239,
1997
+ githubUrl: null,
1998
+ visibility: "public",
1999
+ source: "replicate",
2000
+ latestVersionId: "1b8422bc49635c20d0a84e387ed20879c0dd09254ecdb4e75dc4bec10ff94e97",
2001
+ cogVersion: "0.15.5"
2002
+ }
2003
+ }, {
2004
+ id: 'afiaka87/tortoise-tts',
2005
+ provider: 'replicate',
2006
+ name: 'tortoise-tts',
2007
+ contextWindow: 0,
2008
+ tier: 'flagship',
2009
+ capabilities: new Set(['audio']),
2010
+ pricing: {},
2011
+ metadata: {
2012
+ owner: "afiaka87",
2013
+ description: "Generate speech from text, clone voices from mp3 files. From James Betker AKA \"neonbjb\".",
2014
+ runCount: 172566,
2015
+ githubUrl: "https://github.com/afiaka87/tortoise-tts",
2016
+ visibility: "public",
2017
+ source: "replicate",
2018
+ latestVersionId: "e9658de4b325863c4fcdc12d94bb7c9b54cbfe351b7ca1b36860008172b91c71",
2019
+ cogVersion: "0.3.13"
2020
+ }
2021
+ }, {
2022
+ id: 'suno-ai/bark',
2023
+ provider: 'replicate',
2024
+ name: 'bark',
2025
+ contextWindow: 0,
2026
+ tier: 'flagship',
2027
+ capabilities: new Set(['chat']),
2028
+ pricing: {},
2029
+ metadata: {
2030
+ owner: "suno-ai",
2031
+ description: "🔊 Text-Prompted Generative Audio Model",
2032
+ runCount: 302032,
2033
+ githubUrl: "https://github.com/chenxwh/bark",
2034
+ visibility: "public",
2035
+ source: "replicate",
2036
+ latestVersionId: "b76242b40d67c76ab6742e987628a2a9ac019e11d56ab96c4e91ce03b79b2787",
2037
+ cogVersion: "0.7.0-beta19"
2038
+ }
2039
+ }, {
2040
+ id: 'cjwbw/seamless_communication',
2041
+ provider: 'replicate',
2042
+ name: 'seamless_communication',
2043
+ contextWindow: 0,
2044
+ tier: 'flagship',
2045
+ capabilities: new Set(['chat']),
2046
+ pricing: {},
2047
+ metadata: {
2048
+ owner: "cjwbw",
2049
+ description: "SeamlessM4T—Massively Multilingual & Multimodal Machine Translation",
2050
+ runCount: 88992,
2051
+ githubUrl: "https://github.com/chenxwh/seamless_communication",
2052
+ visibility: "public",
2053
+ source: "replicate",
2054
+ latestVersionId: "668a4fec05a887143e5fe8d45df25ec4c794dd43169b9a11562309b2d45873b0",
2055
+ cogVersion: "0.8.3"
2056
+ }
2057
+ }, {
2058
+ id: 'zsxkib/realistic-voice-cloning',
2059
+ provider: 'replicate',
2060
+ name: 'realistic-voice-cloning',
2061
+ contextWindow: 0,
2062
+ tier: 'flagship',
2063
+ capabilities: new Set(['audio']),
2064
+ pricing: {},
2065
+ metadata: {
2066
+ owner: "zsxkib",
2067
+ description: "Create song covers with any RVC v2 trained AI voice from audio files.",
2068
+ runCount: 1150567,
2069
+ githubUrl: "https://github.com/zsxkib/AICoverGen.git",
2070
+ visibility: "public",
2071
+ source: "replicate",
2072
+ latestVersionId: "0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
2073
+ cogVersion: "0.8.6"
2074
+ }
2075
+ }, {
2076
+ id: 'lucataco/xtts-v2',
2077
+ provider: 'replicate',
2078
+ name: 'xtts-v2',
2079
+ contextWindow: 0,
2080
+ tier: 'flagship',
2081
+ capabilities: new Set(['audio']),
2082
+ pricing: {},
2083
+ metadata: {
2084
+ owner: "lucataco",
2085
+ description: "Coqui XTTS-v2: Multilingual Text To Speech Voice Cloning",
2086
+ runCount: 4391086,
2087
+ githubUrl: "https://github.com/lucataco/cog-xtts-v2",
2088
+ visibility: "public",
2089
+ source: "replicate",
2090
+ latestVersionId: "684bc3855b37866c0c65add2ff39c78f3dea3f4ff103a436465326e0f438d55e",
2091
+ cogVersion: "0.8.6"
2092
+ }
2093
+ }, {
2094
+ id: 'nicknaskida/whisper-diarization',
2095
+ provider: 'replicate',
2096
+ name: 'whisper-diarization',
2097
+ contextWindow: 0,
2098
+ tier: 'flagship',
2099
+ capabilities: new Set(['hearing']),
2100
+ pricing: {},
2101
+ metadata: {
2102
+ owner: "nicknaskida",
2103
+ description: "⚡️ Insanely Fast audio transcription | whisper large-v3 | speaker diarization | word & sentence level timestamps | prompt | hotwords. Fork of thomasmol/whisper-diarization. Added batched whisper, 3x-4x speedup 🚀",
2104
+ runCount: 438,
2105
+ githubUrl: "https://github.com/NickNaskida/cog-whisper-diarization",
2106
+ visibility: "public",
2107
+ source: "replicate",
2108
+ latestVersionId: "c643440e783b6d1dcaef96ba97f2034ac61f02df8a3f2ae0481164ec38e8ac0d",
2109
+ cogVersion: "0.9.20"
2110
+ }
2111
+ }, {
2112
+ id: 'm1guelpf/whisper-subtitles',
2113
+ provider: 'replicate',
2114
+ name: 'whisper-subtitles',
2115
+ contextWindow: 0,
2116
+ tier: 'flagship',
2117
+ capabilities: new Set(['hearing']),
2118
+ pricing: {},
2119
+ metadata: {
2120
+ owner: "m1guelpf",
2121
+ description: "Generate subtitles from an audio file, using OpenAI's Whisper model.",
2122
+ runCount: 73815,
2123
+ githubUrl: "https://github.com/openai/whisper",
2124
+ visibility: "public",
2125
+ source: "replicate",
2126
+ latestVersionId: "7f686e243a96c7f6f0f481bcef24d688a1369ed3983cea348d1f43b879615766",
2127
+ cogVersion: "0.4.4"
2128
+ }
2129
+ }, {
2130
+ id: 'openai/gpt-4o-transcribe',
2131
+ provider: 'replicate',
2132
+ name: 'gpt-4o-transcribe',
2133
+ contextWindow: 0,
2134
+ tier: 'flagship',
2135
+ capabilities: new Set(['hearing', 'chat', 'streaming']),
2136
+ pricing: {},
2137
+ metadata: {
2138
+ owner: "openai",
2139
+ description: "A speech-to-text model that uses GPT-4o to transcribe audio",
2140
+ runCount: 16933,
2141
+ githubUrl: null,
2142
+ visibility: "public",
2143
+ source: "replicate",
2144
+ latestVersionId: "cf92fe5e0d9a451f2c47c58883af0ff92e3908c138239d8cba7f8646e99657bc",
2145
+ cogVersion: "0.16.8"
2146
+ }
2147
+ }, {
2148
+ id: 'openai/gpt-4o-mini-transcribe',
2149
+ provider: 'replicate',
2150
+ name: 'gpt-4o-mini-transcribe',
2151
+ contextWindow: 0,
2152
+ tier: 'efficient',
2153
+ capabilities: new Set(['hearing', 'chat', 'streaming']),
2154
+ pricing: {},
2155
+ metadata: {
2156
+ owner: "openai",
2157
+ description: "A speech-to-text model that uses GPT-4o mini to transcribe audio",
2158
+ runCount: 5203,
2159
+ githubUrl: null,
2160
+ visibility: "public",
2161
+ source: "replicate",
2162
+ latestVersionId: "60b48ed4cd354f9482bf2d4d39df27a6da5191dd93b5f411592da2fdc7e72e2d",
2163
+ cogVersion: "0.16.8"
2164
+ }
2165
+ }, {
2166
+ id: 'adidoes/whisperx-video-transcribe',
2167
+ provider: 'replicate',
2168
+ name: 'whisperx-video-transcribe',
2169
+ contextWindow: 0,
2170
+ tier: 'flagship',
2171
+ capabilities: new Set(['hearing']),
2172
+ pricing: {},
2173
+ metadata: {
2174
+ owner: "adidoes",
2175
+ description: "ASR from video URL based on whisperx using large-v2 model",
2176
+ runCount: 19586,
2177
+ githubUrl: "https://github.com/adidoes/cog-whisperx-video-transcribe",
2178
+ visibility: "public",
2179
+ source: "replicate",
2180
+ latestVersionId: "481284a2a2ff72a031689481ca92fb1d20b194980a4b435d93f6f4c9520fea61",
2181
+ cogVersion: "0.8.6"
2182
+ }
2183
+ }, {
2184
+ id: 'daanelson/whisperx',
2185
+ provider: 'replicate',
2186
+ name: 'whisperx',
2187
+ contextWindow: 0,
2188
+ tier: 'flagship',
2189
+ capabilities: new Set(['hearing']),
2190
+ pricing: {},
2191
+ metadata: {
2192
+ owner: "daanelson",
2193
+ description: "Accelerated transcription of audio using WhisperX",
2194
+ runCount: 89679,
2195
+ githubUrl: "https://github.com/daanelson/cog-whisperx",
2196
+ visibility: "public",
2197
+ source: "replicate",
2198
+ latestVersionId: "9aa6ecadd30610b81119fc1b6807302fd18ca6cbb39b3216f430dcf23618cedd",
2199
+ cogVersion: "0.8.0-beta8"
2200
+ }
2201
+ }, {
2202
+ id: 'openai/whisper',
2203
+ provider: 'replicate',
2204
+ name: 'whisper',
2205
+ contextWindow: 0,
2206
+ tier: 'flagship',
2207
+ capabilities: new Set(['hearing']),
2208
+ pricing: {},
2209
+ metadata: {
2210
+ owner: "openai",
2211
+ description: "Convert speech in audio to text",
2212
+ runCount: 138329405,
2213
+ githubUrl: "https://github.com/replicate/cog-whisper",
2214
+ visibility: "public",
2215
+ source: "replicate",
2216
+ latestVersionId: "8099696689d249cf8b122d833c36ac3f75505c666a395ca40ef26f68e7d3d16e",
2217
+ cogVersion: "0.13.2"
2218
+ }
2219
+ }, {
2220
+ id: 'thomasmol/whisper-diarization',
2221
+ provider: 'replicate',
2222
+ name: 'whisper-diarization',
2223
+ contextWindow: 0,
2224
+ tier: 'flagship',
2225
+ capabilities: new Set(['hearing']),
2226
+ pricing: {},
2227
+ metadata: {
2228
+ owner: "thomasmol",
2229
+ description: "⚡️ Blazing fast audio transcription with speaker diarization | Whisper Large V3 Turbo | word & sentence level timestamps | prompt",
2230
+ runCount: 3367229,
2231
+ githubUrl: "https://github.com/thomasmol/cog-whisper-diarization",
2232
+ visibility: "public",
2233
+ source: "replicate",
2234
+ latestVersionId: "1495a9cddc83b2203b0d8d3516e38b80fd1572ebc4bc5700ac1da56a9b3ed886",
2235
+ cogVersion: "0.13.7"
2236
+ }
2237
+ }, {
2238
+ id: 'vaibhavs10/incredibly-fast-whisper',
2239
+ provider: 'replicate',
2240
+ name: 'incredibly-fast-whisper',
2241
+ contextWindow: 0,
2242
+ tier: 'flagship',
2243
+ capabilities: new Set(['hearing']),
2244
+ pricing: {},
2245
+ metadata: {
2246
+ owner: "vaibhavs10",
2247
+ description: "whisper-large-v3, incredibly fast, powered by Hugging Face Transformers! 🤗",
2248
+ runCount: 18259708,
2249
+ githubUrl: "https://github.com/chenxwh/insanely-fast-whisper",
2250
+ visibility: "public",
2251
+ source: "replicate",
2252
+ latestVersionId: "3ab86df6c8f54c11309d4d1f930ac292bad43ace52d10c80d87eb258b3c9f79c",
2253
+ cogVersion: "0.9.4"
2254
+ }
2255
+ }, {
2256
+ id: 'cjwbw/canary-1b',
2257
+ provider: 'replicate',
2258
+ name: 'canary-1b',
2259
+ contextWindow: 0,
2260
+ tier: 'flagship',
2261
+ capabilities: new Set(['hearing']),
2262
+ pricing: {},
2263
+ metadata: {
2264
+ owner: "cjwbw",
2265
+ description: "Nvidia Automatic speech-to-text recognition (ASR) in 4 languages (English, German, French, Spanish)",
2266
+ runCount: 277,
2267
+ githubUrl: "https://github.com/chenxwh/cog-canary",
2268
+ visibility: "public",
2269
+ source: "replicate"
2270
+ }
2271
+ }, {
2272
+ id: 'nvidia/parakeet-rnnt-1.1b',
2273
+ provider: 'replicate',
2274
+ name: 'parakeet-rnnt-1.1b',
2275
+ contextWindow: 0,
2276
+ tier: 'flagship',
2277
+ capabilities: new Set(['hearing']),
2278
+ pricing: {},
2279
+ metadata: {
2280
+ owner: "nvidia",
2281
+ description: "🗣️ Nvidia + Suno.ai's speech-to-text conversion with high accuracy and efficiency 📝",
2282
+ runCount: 18867,
2283
+ githubUrl: "https://github.com/zsxkib/cog-parakeet-rnnt-1.1b",
2284
+ visibility: "public",
2285
+ source: "replicate",
2286
+ latestVersionId: "73ddbebaef172a47c8dfdd79381f110bfdc7691bcc7a4edde82f0a39e380ce50",
2287
+ cogVersion: "0.8.6"
2288
+ }
2289
+ }, {
2290
+ id: 'victor-upmeet/whisperx',
2291
+ provider: 'replicate',
2292
+ name: 'whisperx',
2293
+ contextWindow: 0,
2294
+ tier: 'flagship',
2295
+ capabilities: new Set(['hearing']),
2296
+ pricing: {},
2297
+ metadata: {
2298
+ owner: "victor-upmeet",
2299
+ description: "Accelerated transcription, word-level timestamps and diarization with whisperX large-v3",
2300
+ runCount: 4629134,
2301
+ githubUrl: "https://github.com/victor-upmeet/whisperx-replicate",
2302
+ visibility: "public",
2303
+ source: "replicate",
2304
+ latestVersionId: "84d2ad2d6194fe98a17d2b60bef1c7f910c46b2f6fd38996ca457afd9c8abfcb",
2305
+ cogVersion: "0.9.4"
2306
+ }
2307
+ }, {
2308
+ id: 'wavespeedai/wan-2.1-t2v-480p',
2309
+ provider: 'replicate',
2310
+ name: 'wan-2.1-t2v-480p',
2311
+ contextWindow: 0,
2312
+ tier: 'flagship',
2313
+ capabilities: new Set(['chat']),
2314
+ pricing: {},
2315
+ metadata: {
2316
+ owner: "wavespeedai",
2317
+ description: "Accelerated inference for Wan 2.1 14B text to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.",
2318
+ runCount: 178754,
2319
+ githubUrl: "https://github.com/Wan-Video/Wan2.1",
2320
+ visibility: "public",
2321
+ source: "replicate",
2322
+ latestVersionId: "2a0c9a4ce3ab7dcb5aed973f4160b08a12cadedf8ef89e84c7068fc7163ceaf1",
2323
+ cogVersion: "0.16.8"
2324
+ }
2325
+ }, {
2326
+ id: 'wavespeedai/hunyuan-video-fast',
2327
+ provider: 'replicate',
2328
+ name: 'hunyuan-video-fast',
2329
+ contextWindow: 0,
2330
+ tier: 'flagship',
2331
+ capabilities: new Set([]),
2332
+ pricing: {},
2333
+ metadata: {
2334
+ owner: "wavespeedai",
2335
+ description: "Accelerated inference for HunyuanVideo with high resolution (1280x720), a state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions",
2336
+ runCount: 5007,
2337
+ githubUrl: "https://github.com/Tencent/HunyuanVideo",
2338
+ visibility: "public",
2339
+ source: "replicate"
2340
+ }
2341
+ }, {
2342
+ id: 'meta/sam-2-video',
2343
+ provider: 'replicate',
2344
+ name: 'sam-2-video',
2345
+ contextWindow: 0,
2346
+ tier: 'flagship',
2347
+ capabilities: new Set(['chat']),
2348
+ pricing: {},
2349
+ metadata: {
2350
+ owner: "meta",
2351
+ description: "SAM 2: Segment Anything v2 (for videos)",
2352
+ runCount: 46719,
2353
+ githubUrl: "https://github.com/zsxkib/segment-anything-2/tree/video",
2354
+ visibility: "public",
2355
+ source: "replicate",
2356
+ latestVersionId: "33432afdfc06a10da6b4018932893d39b0159f838b6d11dd1236dff85cc5ec1d",
2357
+ cogVersion: "0.9.14"
2358
+ }
2359
+ }, {
2360
+ id: 'luma/ray-flash-2-540p',
2361
+ provider: 'replicate',
2362
+ name: 'ray-flash-2-540p',
2363
+ contextWindow: 0,
2364
+ tier: 'flagship',
2365
+ capabilities: new Set(['chat']),
2366
+ pricing: {},
2367
+ metadata: {
2368
+ owner: "luma",
2369
+ description: "Generate 5s and 9s 540p videos, faster and cheaper than Ray 2",
2370
+ runCount: 53842,
2371
+ githubUrl: null,
2372
+ visibility: "public",
2373
+ source: "replicate",
2374
+ latestVersionId: "4713d00f08979857aaaf91fcaf6a3b4da55e76bd0de435bc7d5db176fc526346",
2375
+ cogVersion: "0.16.8"
2376
+ }
2377
+ }, {
2378
+ id: 'luma/ray-flash-2-720p',
2379
+ provider: 'replicate',
2380
+ name: 'ray-flash-2-720p',
2381
+ contextWindow: 0,
2382
+ tier: 'flagship',
2383
+ capabilities: new Set(['chat']),
2384
+ pricing: {},
2385
+ metadata: {
2386
+ owner: "luma",
2387
+ description: "Generate 5s and 9s 720p videos, faster and cheaper than Ray 2",
2388
+ runCount: 37310,
2389
+ githubUrl: null,
2390
+ visibility: "public",
2391
+ source: "replicate",
2392
+ latestVersionId: "8d013ce454f92380dcfd7a497f692172c2d352121801356285559eee26c934bb",
2393
+ cogVersion: "0.16.8"
2394
+ }
2395
+ }, {
2396
+ id: 'pixverse/pixverse-v4',
2397
+ provider: 'replicate',
2398
+ name: 'pixverse-v4',
2399
+ contextWindow: 0,
2400
+ tier: 'flagship',
2401
+ capabilities: new Set(['chat']),
2402
+ pricing: {},
2403
+ metadata: {
2404
+ owner: "pixverse",
2405
+ description: "Quickly generate smooth 5s or 8s videos at 540p, 720p or 1080p",
2406
+ runCount: 32721,
2407
+ githubUrl: null,
2408
+ visibility: "public",
2409
+ source: "replicate",
2410
+ latestVersionId: "b81eb132d4ea29f56b316c85f69502838d7df40b1bd017955218adac032615ca",
2411
+ cogVersion: "0.16.7"
2412
+ }
2413
+ }, {
2414
+ id: 'leonardoai/motion-2.0',
2415
+ provider: 'replicate',
2416
+ name: 'motion-2.0',
2417
+ contextWindow: 0,
2418
+ tier: 'flagship',
2419
+ capabilities: new Set(['chat']),
2420
+ pricing: {},
2421
+ metadata: {
2422
+ owner: "leonardoai",
2423
+ description: "Create 5s 480p videos from a text prompt",
2424
+ runCount: 8494,
2425
+ githubUrl: null,
2426
+ visibility: "public",
2427
+ source: "replicate",
2428
+ latestVersionId: "d04d296a496f3e43a6da299acc29a90a1dbe673ba8f9e058ce5f02ae60f2df92",
2429
+ cogVersion: "0.16.7"
2430
+ }
2431
+ }, {
2432
+ id: 'wan-video/wan-2.2-i2v-a14b',
2433
+ provider: 'replicate',
2434
+ name: 'wan-2.2-i2v-a14b',
2435
+ contextWindow: 0,
2436
+ tier: 'flagship',
2437
+ capabilities: new Set(['chat']),
2438
+ pricing: {},
2439
+ metadata: {
2440
+ owner: "wan-video",
2441
+ description: "Image-to-video at 720p and 480p with Wan 2.2 A14B",
2442
+ runCount: 39216,
2443
+ githubUrl: null,
2444
+ visibility: "public",
2445
+ source: "replicate",
2446
+ latestVersionId: "2c62e0842338726c74ad99a3c469255ce3f4c1f66ee000c265451b87754ac0c9",
2447
+ cogVersion: "0.15.9"
2448
+ }
2449
+ }, {
2450
+ id: 'wan-video/wan-2.1-1.3b',
2451
+ provider: 'replicate',
2452
+ name: 'wan-2.1-1.3b',
2453
+ contextWindow: 0,
2454
+ tier: 'flagship',
2455
+ capabilities: new Set(['chat']),
2456
+ pricing: {},
2457
+ metadata: {
2458
+ owner: "wan-video",
2459
+ description: "Generate 5s 480p videos. Wan is an advanced and powerful visual generation model developed by Tongyi Lab of Alibaba Group",
2460
+ runCount: 43640,
2461
+ githubUrl: "https://github.com/Wan-Video/Wan2.1",
2462
+ visibility: "public",
2463
+ source: "replicate",
2464
+ latestVersionId: "121bbb762bf449889f090d36e3598c72c50c7a8cc2ce250433bc521a562aae61",
2465
+ cogVersion: "0.14.0-alpha1"
2466
+ }
2467
+ }, {
2468
+ id: 'andreasjansson/tile-morph',
2469
+ provider: 'replicate',
2470
+ name: 'tile-morph',
2471
+ contextWindow: 0,
2472
+ tier: 'flagship',
2473
+ capabilities: new Set(['chat']),
2474
+ pricing: {},
2475
+ metadata: {
2476
+ owner: "andreasjansson",
2477
+ description: "Create tileable animations with seamless transitions",
2478
+ runCount: 529342,
2479
+ githubUrl: "https://github.com/andreasjansson/tile-morph",
2480
+ visibility: "public",
2481
+ source: "replicate",
2482
+ latestVersionId: "cbf059cce30a22d821a3c86309ae3b037dcd505dd2eba47f8ea6eba20adced85",
2483
+ cogVersion: "0.6.1"
2484
+ }
2485
+ }, {
2486
+ id: 'open-mmlab/pia',
2487
+ provider: 'replicate',
2488
+ name: 'pia',
2489
+ contextWindow: 0,
2490
+ tier: 'flagship',
2491
+ capabilities: new Set(['chat']),
2492
+ pricing: {},
2493
+ metadata: {
2494
+ owner: "open-mmlab",
2495
+ description: "Personalized Image Animator",
2496
+ runCount: 103501,
2497
+ githubUrl: "https://github.com/chenxwh/PIA",
2498
+ visibility: "public",
2499
+ source: "replicate",
2500
+ latestVersionId: "7a673cec329e8f9c51a96791030103467e04aad905cc0319ad6501eb2d54e91b",
2501
+ cogVersion: "0.8.6"
2502
+ }
2503
+ }, {
2504
+ id: 'fofr/tooncrafter',
2505
+ provider: 'replicate',
2506
+ name: 'tooncrafter',
2507
+ contextWindow: 0,
2508
+ tier: 'flagship',
2509
+ capabilities: new Set(['chat']),
2510
+ pricing: {},
2511
+ metadata: {
2512
+ owner: "fofr",
2513
+ description: "Create videos from illustrated input images",
2514
+ runCount: 61113,
2515
+ githubUrl: "https://github.com/fofr/cog-comfyui-tooncrafter",
2516
+ visibility: "public",
2517
+ source: "replicate",
2518
+ latestVersionId: "0486ff07368e816ec3d5c69b9581e7a09b55817f567a0d74caad9395c9295c77",
2519
+ cogVersion: "0.9.7"
2520
+ }
2521
+ }, {
2522
+ id: 'fofr/video-morpher',
2523
+ provider: 'replicate',
2524
+ name: 'video-morpher',
2525
+ contextWindow: 0,
2526
+ tier: 'flagship',
2527
+ capabilities: new Set(['chat']),
2528
+ pricing: {},
2529
+ metadata: {
2530
+ owner: "fofr",
2531
+ description: "Generate a video that morphs between subjects, with an optional style",
2532
+ runCount: 14911,
2533
+ githubUrl: "https://github.com/fofr/cog-video-morpher",
2534
+ visibility: "public",
2535
+ source: "replicate",
2536
+ latestVersionId: "e70e975067d2b5dbe9e2d9022833d27230a1bdeb3f4af6fe6bb49a548a3039a7",
2537
+ cogVersion: "0.9.5"
2538
+ }
2539
+ }, {
2540
+ id: 'zsxkib/hunyuan-video2video',
2541
+ provider: 'replicate',
2542
+ name: 'hunyuan-video2video',
2543
+ contextWindow: 0,
2544
+ tier: 'flagship',
2545
+ capabilities: new Set(['chat']),
2546
+ pricing: {},
2547
+ metadata: {
2548
+ owner: "zsxkib",
2549
+ description: "A state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions",
2550
+ runCount: 2860,
2551
+ githubUrl: null,
2552
+ visibility: "public",
2553
+ source: "replicate",
2554
+ latestVersionId: "d550f226f28b1030c2fedd2947f39f19b4b0233b50364904538caaf037fb18d3",
2555
+ cogVersion: "0.13.6"
2556
+ }
2557
+ }, {
2558
+ id: 'pixverse/pixverse-v4.5',
2559
+ provider: 'replicate',
2560
+ name: 'pixverse-v4.5',
2561
+ contextWindow: 0,
2562
+ tier: 'flagship',
2563
+ capabilities: new Set(['chat']),
2564
+ pricing: {},
2565
+ metadata: {
2566
+ owner: "pixverse",
2567
+ description: "Quickly make 5s or 8s videos at 540p, 720p or 1080p. It has enhanced motion, prompt coherence and handles complex actions well.",
2568
+ runCount: 187042,
2569
+ githubUrl: null,
2570
+ visibility: "public",
2571
+ source: "replicate",
2572
+ latestVersionId: "34a26b8422fba877262d6ae16255812f3e862c88fd8a42949bba145cd7c8a35d",
2573
+ cogVersion: "0.16.7"
2574
+ }
2575
+ }, {
2576
+ id: 'google/veo-3',
2577
+ provider: 'replicate',
2578
+ name: 'veo-3',
2579
+ contextWindow: 0,
2580
+ tier: 'flagship',
2581
+ capabilities: new Set(['chat']),
2582
+ pricing: {},
2583
+ metadata: {
2584
+ owner: "google",
2585
+ description: "Sound on: Google’s flagship Veo 3 text to video model, with audio",
2586
+ runCount: 190479,
2587
+ githubUrl: null,
2588
+ visibility: "public",
2589
+ source: "replicate",
2590
+ latestVersionId: "08f6f9b08fc4b0500cbd7a2c2a4f38dfcd02af26b535dda5658a8aefafdedab5",
2591
+ cogVersion: "0.16.8"
2592
+ }
2593
+ }, {
2594
+ id: 'minimax/video-01-live',
2595
+ provider: 'replicate',
2596
+ name: 'video-01-live',
2597
+ contextWindow: 0,
2598
+ tier: 'flagship',
2599
+ capabilities: new Set(['chat']),
2600
+ pricing: {},
2601
+ metadata: {
2602
+ owner: "minimax",
2603
+ description: "An image-to-video (I2V) model specifically trained for Live2D and general animation use cases",
2604
+ runCount: 169133,
2605
+ githubUrl: null,
2606
+ visibility: "public",
2607
+ source: "replicate",
2608
+ latestVersionId: "b3fd893b518666a710738c15185940144fce6987432a31768a8e0ffba7f3359b",
2609
+ cogVersion: "0.15.8"
2610
+ }
2611
+ }, {
2612
+ id: 'wavespeedai/wan-2.1-i2v-720p',
2613
+ provider: 'replicate',
2614
+ name: 'wan-2.1-i2v-720p',
2615
+ contextWindow: 0,
2616
+ tier: 'flagship',
2617
+ capabilities: new Set(['chat']),
2618
+ pricing: {},
2619
+ metadata: {
2620
+ owner: "wavespeedai",
2621
+ description: "Accelerated inference for Wan 2.1 14B image to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.",
2622
+ runCount: 84964,
2623
+ githubUrl: "https://github.com/Wan-Video/Wan2.1",
2624
+ visibility: "public",
2625
+ source: "replicate",
2626
+ latestVersionId: "03061ea1ee4c36167161619dbeceb5950c4389995fbfc2dde92dfb925023a9d8",
2627
+ cogVersion: "0.16.8"
2628
+ }
2629
+ }, {
2630
+ id: 'wavespeedai/wan-2.1-i2v-480p',
2631
+ provider: 'replicate',
2632
+ name: 'wan-2.1-i2v-480p',
2633
+ contextWindow: 0,
2634
+ tier: 'flagship',
2635
+ capabilities: new Set(['chat']),
2636
+ pricing: {},
2637
+ metadata: {
2638
+ owner: "wavespeedai",
2639
+ description: "Accelerated inference for Wan 2.1 14B image to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.",
2640
+ runCount: 423373,
2641
+ githubUrl: "https://github.com/Wan-Video/Wan2.1",
2642
+ visibility: "public",
2643
+ source: "replicate",
2644
+ latestVersionId: "aaa7bb3e9359f994850a1c66ec804cf2c2d0ca72ffedf84552d27106c3e69ed7",
2645
+ cogVersion: "0.16.8"
2646
+ }
2647
+ }, {
2648
+ id: 'wavespeedai/wan-2.1-t2v-720p',
2649
+ provider: 'replicate',
2650
+ name: 'wan-2.1-t2v-720p',
2651
+ contextWindow: 0,
2652
+ tier: 'flagship',
2653
+ capabilities: new Set(['chat']),
2654
+ pricing: {},
2655
+ metadata: {
2656
+ owner: "wavespeedai",
2657
+ description: "Accelerated inference for Wan 2.1 14B text to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.",
2658
+ runCount: 34868,
2659
+ githubUrl: "https://github.com/Wan-Video/Wan2.1",
2660
+ visibility: "public",
2661
+ source: "replicate",
2662
+ latestVersionId: "b67cfd64df4f938f279c6170c7b964b0b4dfcaab0f232e4d2aefd0b8d206b440",
2663
+ cogVersion: "0.16.8"
2664
+ }
2665
+ }, {
2666
+ id: 'google/veo-2',
2667
+ provider: 'replicate',
2668
+ name: 'veo-2',
2669
+ contextWindow: 0,
2670
+ tier: 'flagship',
2671
+ capabilities: new Set(['chat']),
2672
+ pricing: {},
2673
+ metadata: {
2674
+ owner: "google",
2675
+ description: "State of the art video generation model. Veo 2 can faithfully follow simple and complex instructions, and convincingly simulates real-world physics as well as a wide range of visual styles.",
2676
+ runCount: 100697,
2677
+ githubUrl: null,
2678
+ visibility: "public",
2679
+ source: "replicate",
2680
+ latestVersionId: "0546b4e90d4f215c7fc42c9b8d815df3a7b6e47a754ee94ddb62b3f667fea9a5",
2681
+ cogVersion: "0.15.0"
2682
+ }
2683
+ }, {
2684
+ id: 'kwaivgi/kling-v2.1-master',
2685
+ provider: 'replicate',
2686
+ name: 'kling-v2.1-master',
2687
+ contextWindow: 0,
2688
+ tier: 'flagship',
2689
+ capabilities: new Set(['chat']),
2690
+ pricing: {},
2691
+ metadata: {
2692
+ owner: "kwaivgi",
2693
+ description: "A premium version of Kling v2.1 with superb dynamics and prompt adherence. Generate 1080p 5s and 10s videos from text or an image",
2694
+ runCount: 62044,
2695
+ githubUrl: null,
2696
+ visibility: "public",
2697
+ source: "replicate",
2698
+ latestVersionId: "cd4c2cf153b6dedd2bb1130b1947b2391334a8be448cfe3288f1046f2eed595e",
2699
+ cogVersion: "0.16.7"
2700
+ }
2701
+ }, {
2702
+ id: 'kwaivgi/kling-v2.1',
2703
+ provider: 'replicate',
2704
+ name: 'kling-v2.1',
2705
+ contextWindow: 0,
2706
+ tier: 'flagship',
2707
+ capabilities: new Set(['chat']),
2708
+ pricing: {},
2709
+ metadata: {
2710
+ owner: "kwaivgi",
2711
+ description: "Use Kling v2.1 to generate 5s and 10s videos in 720p and 1080p resolution from a starting image (image-to-video)",
2712
+ runCount: 2343636,
2713
+ githubUrl: null,
2714
+ visibility: "public",
2715
+ source: "replicate",
2716
+ latestVersionId: "8f1d07f812d87339d7866c94ba2149e8ee456472e5c5ec04ac22795e21b55c68",
2717
+ cogVersion: "0.16.7"
2718
+ }
2719
+ }, {
2720
+ id: 'bytedance/seedance-1-lite',
2721
+ provider: 'replicate',
2722
+ name: 'seedance-1-lite',
2723
+ contextWindow: 0,
2724
+ tier: 'flagship',
2725
+ capabilities: new Set(['chat']),
2726
+ pricing: {},
2727
+ metadata: {
2728
+ owner: "bytedance",
2729
+ description: "A video generation model that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 720p resolution",
2730
+ runCount: 1503727,
2731
+ githubUrl: null,
2732
+ visibility: "public",
2733
+ source: "replicate",
2734
+ latestVersionId: "51199a5b030ffe31001db24377ab66bf72741e4201ba6229d713da08b78ac056",
2735
+ cogVersion: "0.16.8"
2736
+ }
2737
+ }, {
2738
+ id: 'google/veo-3-fast',
2739
+ provider: 'replicate',
2740
+ name: 'veo-3-fast',
2741
+ contextWindow: 0,
2742
+ tier: 'flagship',
2743
+ capabilities: new Set(['chat']),
2744
+ pricing: {},
2745
+ metadata: {
2746
+ owner: "google",
2747
+ description: "A faster and cheaper version of Google’s Veo 3 video model, with audio",
2748
+ runCount: 103409,
2749
+ githubUrl: null,
2750
+ visibility: "public",
2751
+ source: "replicate",
2752
+ latestVersionId: "100a06f7df77026a28d962e7cd70c0e8a7356313377e8e0ff8c7a3445d0cdfb2",
2753
+ cogVersion: "0.16.8"
2754
+ }
2755
+ }, {
2756
+ id: 'wan-video/wan-2.2-t2v-fast',
2757
+ provider: 'replicate',
2758
+ name: 'wan-2.2-t2v-fast',
2759
+ contextWindow: 0,
2760
+ tier: 'flagship',
2761
+ capabilities: new Set(['chat']),
2762
+ pricing: {},
2763
+ metadata: {
2764
+ owner: "wan-video",
2765
+ description: "A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B text-to-video",
2766
+ runCount: 101293,
2767
+ githubUrl: null,
2768
+ visibility: "public",
2769
+ source: "replicate",
2770
+ latestVersionId: "1adb67211e01b96e48f9ab2bc5da80cac6f07604f2117ffafa729808850ffc0e",
2771
+ cogVersion: "0.15.9"
2772
+ }
2773
+ }, {
2774
+ id: 'minimax/hailuo-02',
2775
+ provider: 'replicate',
2776
+ name: 'hailuo-02',
2777
+ contextWindow: 0,
2778
+ tier: 'flagship',
2779
+ capabilities: new Set(['chat']),
2780
+ pricing: {},
2781
+ metadata: {
2782
+ owner: "minimax",
2783
+ description: "Hailuo 2 is a text-to-video and image-to-video model that can make 6s or 10s videos at 768p (standard) or 1080p (pro). It excels at real world physics.",
2784
+ runCount: 171012,
2785
+ githubUrl: null,
2786
+ visibility: "public",
2787
+ source: "replicate",
2788
+ latestVersionId: "155f1a7a8b1f92ab533dd0c0ad96956d07813807901fe117282c20c965b560ca",
2789
+ cogVersion: "0.16.7"
2790
+ }
2791
+ }, {
2792
+ id: 'fofr/not-real',
2793
+ provider: 'replicate',
2794
+ name: 'not-real',
2795
+ contextWindow: 0,
2796
+ tier: 'flagship',
2797
+ capabilities: new Set(['chat']),
2798
+ pricing: {},
2799
+ metadata: {
2800
+ owner: "fofr",
2801
+ description: "Make a very realistic looking real-world AI video",
2802
+ runCount: 2218,
2803
+ githubUrl: null,
2804
+ visibility: "public",
2805
+ source: "replicate",
2806
+ latestVersionId: "19b3a157a2bee49509ea771214bdc645dbaae3b8dd0d71d99bbf802c69fbbe2b",
2807
+ cogVersion: "0.14.0"
2808
+ }
2809
+ }, {
2810
+ id: 'wan-video/wan-2.2-i2v-fast',
2811
+ provider: 'replicate',
2812
+ name: 'wan-2.2-i2v-fast',
2813
+ contextWindow: 0,
2814
+ tier: 'flagship',
2815
+ capabilities: new Set(['chat']),
2816
+ pricing: {},
2817
+ metadata: {
2818
+ owner: "wan-video",
2819
+ description: "A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B image-to-video",
2820
+ runCount: 2303117,
2821
+ githubUrl: null,
2822
+ visibility: "public",
2823
+ source: "replicate",
2824
+ latestVersionId: "b609b267d986d762a6d8679ac036d29e6d4454218df558db3aa4d0396ba55c59",
2825
+ cogVersion: "0.15.9"
2826
+ }
2827
+ }, {
2828
+ id: 'kwaivgi/kling-v1.6-pro',
2829
+ provider: 'replicate',
2830
+ name: 'kling-v1.6-pro',
2831
+ contextWindow: 0,
2832
+ tier: 'flagship',
2833
+ capabilities: new Set(['chat']),
2834
+ pricing: {},
2835
+ metadata: {
2836
+ owner: "kwaivgi",
2837
+ description: "Generate 5s and 10s videos in 1080p resolution",
2838
+ runCount: 751326,
2839
+ githubUrl: null,
2840
+ visibility: "public",
2841
+ source: "replicate",
2842
+ latestVersionId: "478bea206ec92bfb5aec602a24c2ad041040294cb4dec793d5f4fba85b69ac66",
2843
+ cogVersion: "0.16.7"
2844
+ }
2845
+ }, {
2846
+ id: 'kwaivgi/kling-v2.0',
2847
+ provider: 'replicate',
2848
+ name: 'kling-v2.0',
2849
+ contextWindow: 0,
2850
+ tier: 'flagship',
2851
+ capabilities: new Set(['chat']),
2852
+ pricing: {},
2853
+ metadata: {
2854
+ owner: "kwaivgi",
2855
+ description: "Generate 5s and 10s videos in 720p resolution",
2856
+ runCount: 78165,
2857
+ githubUrl: null,
2858
+ visibility: "public",
2859
+ source: "replicate",
2860
+ latestVersionId: "07225bf82fdb2e1c3d0f6a9bbc011f73dd8db7ccff646b0cea5335038a8cfcfd",
2861
+ cogVersion: "0.16.7"
2862
+ }
2863
+ }, {
2864
+ id: 'luma/ray',
2865
+ provider: 'replicate',
2866
+ name: 'ray',
2867
+ contextWindow: 0,
2868
+ tier: 'flagship',
2869
+ capabilities: new Set(['chat']),
2870
+ pricing: {},
2871
+ metadata: {
2872
+ owner: "luma",
2873
+ description: "Fast, high quality text-to-video and image-to-video (Also known as Dream Machine)",
2874
+ runCount: 57989,
2875
+ githubUrl: null,
2876
+ visibility: "public",
2877
+ source: "replicate",
2878
+ latestVersionId: "3aad05d5871bb7cee90429cc681bf54d330eedb35a8f5a138d84f84b9f3cd706",
2879
+ cogVersion: "0.16.8"
2880
+ }
2881
+ }, {
2882
+ id: 'pixverse/pixverse-v5',
2883
+ provider: 'replicate',
2884
+ name: 'pixverse-v5',
2885
+ contextWindow: 0,
2886
+ tier: 'flagship',
2887
+ capabilities: new Set(['chat']),
2888
+ pricing: {},
2889
+ metadata: {
2890
+ owner: "pixverse",
2891
+ description: "Create 5s-8s videos with enhanced character movement, visual effects, and exclusive 1080p-8s support. Optimized for anime characters and complex actions",
2892
+ runCount: 294623,
2893
+ githubUrl: null,
2894
+ visibility: "public",
2895
+ source: "replicate",
2896
+ latestVersionId: "254433980b4084b64480f0f475fe6799bbd1fd07ecc3ad7f7e4085afc3345727",
2897
+ cogVersion: "0.16.7"
2898
+ }
2899
+ }, {
2900
+ id: 'luma/ray-2-720p',
2901
+ provider: 'replicate',
2902
+ name: 'ray-2-720p',
2903
+ contextWindow: 0,
2904
+ tier: 'flagship',
2905
+ capabilities: new Set(['chat']),
2906
+ pricing: {},
2907
+ metadata: {
2908
+ owner: "luma",
2909
+ description: "Generate 5s and 9s 720p videos",
2910
+ runCount: 29254,
2911
+ githubUrl: null,
2912
+ visibility: "public",
2913
+ source: "replicate",
2914
+ latestVersionId: "1f60ca1d4944845125a7e2e0c6187f68f691a677c61651e94c8466f2bfab6e4a",
2915
+ cogVersion: "0.16.8"
2916
+ }
2917
+ }, {
2918
+ id: 'wan-video/wan-2.5-t2v-fast',
2919
+ provider: 'replicate',
2920
+ name: 'wan-2.5-t2v-fast',
2921
+ contextWindow: 0,
2922
+ tier: 'flagship',
2923
+ capabilities: new Set(['chat']),
2924
+ pricing: {},
2925
+ metadata: {
2926
+ owner: "wan-video",
2927
+ description: "Wan 2.5 text-to-video, optimized for speed",
2928
+ runCount: 8299,
2929
+ githubUrl: null,
2930
+ visibility: "public",
2931
+ source: "replicate",
2932
+ latestVersionId: "f832e84d1281e577861eea81c531b80f70e9214fa5d27dc9f990ce281594d1c0",
2933
+ cogVersion: "0.16.8"
2934
+ }
2935
+ }, {
2936
+ id: 'wan-video/wan-2.5-i2v-fast',
2937
+ provider: 'replicate',
2938
+ name: 'wan-2.5-i2v-fast',
2939
+ contextWindow: 0,
2940
+ tier: 'flagship',
2941
+ capabilities: new Set(['chat']),
2942
+ pricing: {},
2943
+ metadata: {
2944
+ owner: "wan-video",
2945
+ description: "Wan 2.5 image-to-video, optimized for speed",
2946
+ runCount: 12482,
2947
+ githubUrl: null,
2948
+ visibility: "public",
2949
+ source: "replicate",
2950
+ latestVersionId: "d8461ee8f78b188f7f26a1b6cc32be56d037baa6bb604590e1dcdd90ae573b5d",
2951
+ cogVersion: "0.16.8"
2952
+ }
2953
+ }, {
2954
+ id: 'wan-video/wan-2.5-t2v',
2955
+ provider: 'replicate',
2956
+ name: 'wan-2.5-t2v',
2957
+ contextWindow: 0,
2958
+ tier: 'flagship',
2959
+ capabilities: new Set(['chat']),
2960
+ pricing: {},
2961
+ metadata: {
2962
+ owner: "wan-video",
2963
+ description: "Alibaba Wan 2.5 text to video generation model",
2964
+ runCount: 11768,
2965
+ githubUrl: null,
2966
+ visibility: "public",
2967
+ source: "replicate",
2968
+ latestVersionId: "7bd10e43eeab2c8913593623dbde98e91969f71864d2ae86525d0911b0582673",
2969
+ cogVersion: "0.16.8"
2970
+ }
2971
+ }, {
2972
+ id: 'wan-video/wan-2.5-i2v',
2973
+ provider: 'replicate',
2974
+ name: 'wan-2.5-i2v',
2975
+ contextWindow: 0,
2976
+ tier: 'flagship',
2977
+ capabilities: new Set(['chat']),
2978
+ pricing: {},
2979
+ metadata: {
2980
+ owner: "wan-video",
2981
+ description: "Alibaba Wan 2.5 Image to video generation with background audio",
2982
+ runCount: 34757,
2983
+ githubUrl: null,
2984
+ visibility: "public",
2985
+ source: "replicate",
2986
+ latestVersionId: "1ea48766160887634f81802cec771c69b544e70670f6ac43458a5f0685d645d4",
2987
+ cogVersion: "0.16.8"
2988
+ }
2989
+ }, {
2990
+ id: 'kwaivgi/kling-v2.5-turbo-pro',
2991
+ provider: 'replicate',
2992
+ name: 'kling-v2.5-turbo-pro',
2993
+ contextWindow: 0,
2994
+ tier: 'flagship',
2995
+ capabilities: new Set(['chat']),
2996
+ pricing: {},
2997
+ metadata: {
2998
+ owner: "kwaivgi",
2999
+ description: "Kling 2.5 Turbo Pro: Unlock pro-level text-to-video and image-to-video creation with smooth motion, cinematic depth, and remarkable prompt adherence.",
3000
+ runCount: 300409,
3001
+ githubUrl: null,
3002
+ visibility: "public",
3003
+ source: "replicate",
3004
+ latestVersionId: "8428b0b219bd904cadc8bda6c72c16b8727f6f1a7fb424c8deb9ffbd00722daf",
3005
+ cogVersion: "0.16.8"
3006
+ }
3007
+ }, {
3008
+ id: 'kwaivgi/kling-v1.6-standard',
3009
+ provider: 'replicate',
3010
+ name: 'kling-v1.6-standard',
3011
+ contextWindow: 0,
3012
+ tier: 'flagship',
3013
+ capabilities: new Set(['chat']),
3014
+ pricing: {},
3015
+ metadata: {
3016
+ owner: "kwaivgi",
3017
+ description: "Generate 5s and 10s videos in 720p resolution at 30fps",
3018
+ runCount: 1319915,
3019
+ githubUrl: null,
3020
+ visibility: "public",
3021
+ source: "replicate",
3022
+ latestVersionId: "a79b6f8e346976a7e3e85080c02076188a2bb9bf50b40fadcc996845ce826e73",
3023
+ cogVersion: "0.16.7"
3024
+ }
3025
+ }, {
3026
+ id: 'luma/ray-2-540p',
3027
+ provider: 'replicate',
3028
+ name: 'ray-2-540p',
3029
+ contextWindow: 0,
3030
+ tier: 'flagship',
3031
+ capabilities: new Set(['chat']),
3032
+ pricing: {},
3033
+ metadata: {
3034
+ owner: "luma",
3035
+ description: "Generate 5s and 9s 540p videos",
3036
+ runCount: 10271,
3037
+ githubUrl: null,
3038
+ visibility: "public",
3039
+ source: "replicate",
3040
+ latestVersionId: "b185105f51f0f3d9236c7e201c0f331e2fcb5b02e35c7dbdde0602c9d217ee55",
3041
+ cogVersion: "0.16.8"
3042
+ }
3043
+ }, {
3044
+ id: 'minimax/video-01-director',
3045
+ provider: 'replicate',
3046
+ name: 'video-01-director',
3047
+ contextWindow: 0,
3048
+ tier: 'flagship',
3049
+ capabilities: new Set(['chat']),
3050
+ pricing: {},
3051
+ metadata: {
3052
+ owner: "minimax",
3053
+ description: "Generate videos with specific camera movements",
3054
+ runCount: 70599,
3055
+ githubUrl: null,
3056
+ visibility: "public",
3057
+ source: "replicate",
3058
+ latestVersionId: "5cb5333ec4bd38305a5f1c43506c1e2533ae2836b319dbec8922c6ed9eee04c7",
3059
+ cogVersion: "0.16.7"
3060
+ }
3061
+ }, {
3062
+ id: 'bytedance/seedance-1-pro-fast',
3063
+ provider: 'replicate',
3064
+ name: 'seedance-1-pro-fast',
3065
+ contextWindow: 0,
3066
+ tier: 'flagship',
3067
+ capabilities: new Set(['chat']),
3068
+ pricing: {},
3069
+ metadata: {
3070
+ owner: "bytedance",
3071
+ description: "A faster and cheaper version of Seedance 1 Pro",
3072
+ runCount: 5841,
3073
+ githubUrl: null,
3074
+ visibility: "public",
3075
+ source: "replicate",
3076
+ latestVersionId: "35d0e594f4ef1fcfebd9ba65c838254e6a7fbf23de7031c4aecbae793c362b60",
3077
+ cogVersion: "0.16.8"
3078
+ }
3079
+ }, {
3080
+ id: 'bytedance/seedance-1-pro',
3081
+ provider: 'replicate',
3082
+ name: 'seedance-1-pro',
3083
+ contextWindow: 0,
3084
+ tier: 'flagship',
3085
+ capabilities: new Set(['chat']),
3086
+ pricing: {},
3087
+ metadata: {
3088
+ owner: "bytedance",
3089
+ description: "A pro version of Seedance that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 1080p resolution",
3090
+ runCount: 846821,
3091
+ githubUrl: null,
3092
+ visibility: "public",
3093
+ source: "replicate",
3094
+ latestVersionId: "93a9baccf0f8a5bde44aa9d89e17d4e3751f885054f0f51527c904f58aaecdb1",
3095
+ cogVersion: "0.16.8"
3096
+ }
3097
+ }, {
3098
+ id: 'lucataco/hotshot-xl',
3099
+ provider: 'replicate',
3100
+ name: 'hotshot-xl',
3101
+ contextWindow: 0,
3102
+ tier: 'flagship',
3103
+ capabilities: new Set(['chat']),
3104
+ pricing: {},
3105
+ metadata: {
3106
+ owner: "lucataco",
3107
+ description: "😊 Hotshot-XL is an AI text-to-GIF model trained to work alongside Stable Diffusion XL",
3108
+ runCount: 828151,
3109
+ githubUrl: "https://github.com/lucataco/cog-hotshot-xl",
3110
+ visibility: "public",
3111
+ source: "replicate",
3112
+ latestVersionId: "78b3a6257e16e4b241245d65c8b2b81ea2e1ff7ed4c55306b511509ddbfd327a",
3113
+ cogVersion: "0.8.6"
3114
+ }
3115
+ }, {
3116
+ id: 'lightricks/ltx-video',
3117
+ provider: 'replicate',
3118
+ name: 'ltx-video',
3119
+ contextWindow: 0,
3120
+ tier: 'flagship',
3121
+ capabilities: new Set(['chat']),
3122
+ pricing: {},
3123
+ metadata: {
3124
+ owner: "lightricks",
3125
+ description: "LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 24 FPS videos at a 768x512 resolution faster than they can be watched.",
3126
+ runCount: 160569,
3127
+ githubUrl: "https://github.com/Lightricks/LTX-Video",
3128
+ visibility: "public",
3129
+ source: "replicate",
3130
+ latestVersionId: "8c47da666861d081eeb4d1261853087de23923a268a69b63febdf5dc1dee08e4",
3131
+ cogVersion: "0.13.0"
3132
+ }
3133
+ }, {
3134
+ id: 'arielreplicate/deoldify_video',
3135
+ provider: 'replicate',
3136
+ name: 'deoldify_video',
3137
+ contextWindow: 0,
3138
+ tier: 'flagship',
3139
+ capabilities: new Set(['chat']),
3140
+ pricing: {},
3141
+ metadata: {
3142
+ owner: "arielreplicate",
3143
+ description: "Add colours to old video footage.",
3144
+ runCount: 6780,
3145
+ githubUrl: "https://github.com/ArielReplicate/DeOldify",
3146
+ visibility: "public",
3147
+ source: "replicate",
3148
+ latestVersionId: "8f1189b476fcb54cfbe1d07d97b025c571a2ce4e9a7a9558640c78647576e16f",
3149
+ cogVersion: "0.6.1"
3150
+ }
3151
+ }, {
3152
+ id: 'cjwbw/text2video-zero',
3153
+ provider: 'replicate',
3154
+ name: 'text2video-zero',
3155
+ contextWindow: 0,
3156
+ tier: 'flagship',
3157
+ capabilities: new Set(['image']),
3158
+ pricing: {},
3159
+ metadata: {
3160
+ owner: "cjwbw",
3161
+ description: "Text-to-Image Diffusion Models are Zero-Shot Video Generators",
3162
+ runCount: 42002,
3163
+ githubUrl: "https://github.com/chenxwh/Text2Video-Zero",
3164
+ visibility: "public",
3165
+ source: "replicate",
3166
+ latestVersionId: "e671ffe4e976c0ec813f15a9836ebcfd08857ac2669af6917e3c2549307f9fae",
3167
+ cogVersion: "0.6.1"
3168
+ }
3169
+ }, {
3170
+ id: 'zsxkib/pyramid-flow',
3171
+ provider: 'replicate',
3172
+ name: 'pyramid-flow',
3173
+ contextWindow: 0,
3174
+ tier: 'flagship',
3175
+ capabilities: new Set(['chat']),
3176
+ pricing: {},
3177
+ metadata: {
3178
+ owner: "zsxkib",
3179
+ description: "Text-to-Video + Image-to-Video: Pyramid Flow Autoregressive Video Generation method based on Flow Matching",
3180
+ runCount: 8946,
3181
+ githubUrl: "https://github.com/zsxkib/cog-pyramid-flow/tree/replicate",
3182
+ visibility: "public",
3183
+ source: "replicate",
3184
+ latestVersionId: "8e221e66498a52bb3a928a4b49d85379c99ca60fec41511265deec35d547c1fb",
3185
+ cogVersion: "0.9.25"
3186
+ }
3187
+ }, {
3188
+ id: 'anotherjesse/zeroscope-v2-xl',
3189
+ provider: 'replicate',
3190
+ name: 'zeroscope-v2-xl',
3191
+ contextWindow: 0,
3192
+ tier: 'flagship',
3193
+ capabilities: new Set(['chat']),
3194
+ pricing: {},
3195
+ metadata: {
3196
+ owner: "anotherjesse",
3197
+ description: "Zeroscope V2 XL & 576w",
3198
+ runCount: 297641,
3199
+ githubUrl: "https://github.com/anotherjesse/cog-text2video",
3200
+ visibility: "public",
3201
+ source: "replicate",
3202
+ latestVersionId: "9f747673945c62801b13b84701c783929c0ee784e4748ec062204894dda1a351",
3203
+ cogVersion: "v0.8.0-beta7+dev"
3204
+ }
3205
+ }, {
3206
+ id: 'nateraw/stable-diffusion-videos',
3207
+ provider: 'replicate',
3208
+ name: 'stable-diffusion-videos',
3209
+ contextWindow: 0,
3210
+ tier: 'flagship',
3211
+ capabilities: new Set(['image']),
3212
+ pricing: {},
3213
+ metadata: {
3214
+ owner: "nateraw",
3215
+ description: "Generate videos by interpolating the latent space of Stable Diffusion",
3216
+ runCount: 58489,
3217
+ githubUrl: "https://github.com/nateraw/stable-diffusion-videos",
3218
+ visibility: "public",
3219
+ source: "replicate",
3220
+ latestVersionId: "2d87f0f8bc282042002f8d24458bbf588eee5e8d8fffb6fbb10ed48d1dac409e",
3221
+ cogVersion: "0.4.2"
3222
+ }
3223
+ }, {
3224
+ id: 'deforum/deforum_stable_diffusion',
3225
+ provider: 'replicate',
3226
+ name: 'deforum_stable_diffusion',
3227
+ contextWindow: 0,
3228
+ tier: 'flagship',
3229
+ capabilities: new Set(['chat']),
3230
+ pricing: {},
3231
+ metadata: {
3232
+ owner: "deforum",
3233
+ description: "Animating prompts with stable diffusion",
3234
+ runCount: 265652,
3235
+ githubUrl: "https://github.com/deforum/stable-diffusion",
3236
+ visibility: "public",
3237
+ source: "replicate",
3238
+ latestVersionId: "e22e77495f2fb83c34d5fae2ad8ab63c0a87b6b573b6208e1535b23b89ea66d6",
3239
+ cogVersion: "0.4.2"
3240
+ }
3241
+ }, {
3242
+ id: 'ali-vilab/i2vgen-xl',
3243
+ provider: 'replicate',
3244
+ name: 'i2vgen-xl',
3245
+ contextWindow: 0,
3246
+ tier: 'flagship',
3247
+ capabilities: new Set(['chat']),
3248
+ pricing: {},
3249
+ metadata: {
3250
+ owner: "ali-vilab",
3251
+ description: "RESEARCH/NON-COMMERCIAL USE ONLY: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models",
3252
+ runCount: 128018,
3253
+ githubUrl: "https://github.com/chenxwh/i2vgen-xl",
3254
+ visibility: "public",
3255
+ source: "replicate",
3256
+ latestVersionId: "5821a338d00033abaaba89080a17eb8783d9a17ed710a6b4246a18e0900ccad4",
3257
+ cogVersion: "0.8.6"
3258
+ }
3259
+ }, {
3260
+ id: 'minimax/video-01',
3261
+ provider: 'replicate',
3262
+ name: 'video-01',
3263
+ contextWindow: 0,
3264
+ tier: 'flagship',
3265
+ capabilities: new Set(['chat']),
3266
+ pricing: {},
3267
+ metadata: {
3268
+ owner: "minimax",
3269
+ description: "Generate 6s videos with prompts or images. (Also known as Hailuo). Use a subject reference to make a video with a character and the S2V-01 model.",
3270
+ runCount: 603342,
3271
+ githubUrl: null,
3272
+ visibility: "public",
3273
+ source: "replicate",
3274
+ latestVersionId: "608bbe118537f175d1078bbe8cb0b4f656992c14fc80b6a07f53c9a8ad304159",
3275
+ cogVersion: "0.16.1"
3276
+ }
3277
+ }, {
3278
+ id: 'andreasjansson/stable-diffusion-animation',
3279
+ provider: 'replicate',
3280
+ name: 'stable-diffusion-animation',
3281
+ contextWindow: 0,
3282
+ tier: 'flagship',
3283
+ capabilities: new Set(['image']),
3284
+ pricing: {},
3285
+ metadata: {
3286
+ owner: "andreasjansson",
3287
+ description: "Animate Stable Diffusion by interpolating between two prompts",
3288
+ runCount: 119431,
3289
+ githubUrl: "https://github.com/andreasjansson/cog-stable-diffusion",
3290
+ visibility: "public",
3291
+ source: "replicate",
3292
+ latestVersionId: "ca1f5e306e5721e19c473e0d094e6603f0456fe759c10715fcd6c1b79242d4a5",
3293
+ cogVersion: "0.4.4"
3294
+ }
3295
+ }, {
3296
+ id: 'zsxkib/animatediff-prompt-travel',
3297
+ provider: 'replicate',
3298
+ name: 'animatediff-prompt-travel',
3299
+ contextWindow: 0,
3300
+ tier: 'flagship',
3301
+ capabilities: new Set(['image']),
3302
+ pricing: {},
3303
+ metadata: {
3304
+ owner: "zsxkib",
3305
+ description: "🎨AnimateDiff Prompt Travel🧭 Seamlessly Navigate and Animate Between Text-to-Image Prompts for Dynamic Visual Narratives",
3306
+ runCount: 5677,
3307
+ githubUrl: "https://github.com/s9roll7/animatediff-cli-prompt-travel",
3308
+ visibility: "public",
3309
+ source: "replicate",
3310
+ latestVersionId: "1b8a8f2725c03b1ff4a0b960079899131c384149d1feba45e4ef43653deb3b5f",
3311
+ cogVersion: "0.8.6"
3312
+ }
3313
+ }, {
3314
+ id: 'cjwbw/controlvideo',
3315
+ provider: 'replicate',
3316
+ name: 'controlvideo',
3317
+ contextWindow: 0,
3318
+ tier: 'flagship',
3319
+ capabilities: new Set(['chat']),
3320
+ pricing: {},
3321
+ metadata: {
3322
+ owner: "cjwbw",
3323
+ description: "Training-free Controllable Text-to-Video Generation",
3324
+ runCount: 2424,
3325
+ githubUrl: "https://github.com/chenxwh/ControlVideo",
3326
+ visibility: "public",
3327
+ source: "replicate",
3328
+ latestVersionId: "91710b3f53c9c1cb958e7bf0ea982d21b666f6a3ff28c1670ee0c08355ced925",
3329
+ cogVersion: "0.7.2"
3330
+ }
3331
+ }, {
3332
+ id: 'cjwbw/damo-text-to-video',
3333
+ provider: 'replicate',
3334
+ name: 'damo-text-to-video',
3335
+ contextWindow: 0,
3336
+ tier: 'flagship',
3337
+ capabilities: new Set(['chat']),
3338
+ pricing: {},
3339
+ metadata: {
3340
+ owner: "cjwbw",
3341
+ description: "Multi-stage text-to-video generation",
3342
+ runCount: 152607,
3343
+ githubUrl: "https://github.com/chenxwh/cog-damo-text2video",
3344
+ visibility: "public",
3345
+ source: "replicate",
3346
+ latestVersionId: "1e205ea73084bd17a0a3b43396e49ba0d6bc2e754e9283b2df49fad2dcf95755",
3347
+ cogVersion: "0.6.1"
3348
+ }
3349
+ }, {
3350
+ id: 'lucataco/animate-diff',
3351
+ provider: 'replicate',
3352
+ name: 'animate-diff',
3353
+ contextWindow: 0,
3354
+ tier: 'flagship',
3355
+ capabilities: new Set(['image']),
3356
+ pricing: {},
3357
+ metadata: {
3358
+ owner: "lucataco",
3359
+ description: "Animate Your Personalized Text-to-Image Diffusion Models",
3360
+ runCount: 317139,
3361
+ githubUrl: "https://github.com/lucataco/cog-animatediff",
3362
+ visibility: "public",
3363
+ source: "replicate",
3364
+ latestVersionId: "beecf59c4aee8d81bf04f0381033dfa10dc16e845b4ae00d281e2fa377e48a9f",
3365
+ cogVersion: "0.8.6"
3366
+ }
3367
+ }, {
3368
+ id: 'zsxkib/animatediff-illusions',
3369
+ provider: 'replicate',
3370
+ name: 'animatediff-illusions',
3371
+ contextWindow: 0,
3372
+ tier: 'flagship',
3373
+ capabilities: new Set(['chat']),
3374
+ pricing: {},
3375
+ metadata: {
3376
+ owner: "zsxkib",
3377
+ description: "Monster Labs' Controlnet QR Code Monster v2 For SD-1.5 on top of AnimateDiff Prompt Travel (Motion Module SD 1.5 v2)",
3378
+ runCount: 10483,
3379
+ githubUrl: "https://github.com/s9roll7/animatediff-cli-prompt-travel",
3380
+ visibility: "public",
3381
+ source: "replicate",
3382
+ latestVersionId: "b3ccb0101402aafd04bfea042950be606223e2abedbad93cf848bfffa072bb61",
3383
+ cogVersion: "0.8.6"
3384
+ }
3385
+ }, {
3386
+ id: 'arielreplicate/stable_diffusion_infinite_zoom',
3387
+ provider: 'replicate',
3388
+ name: 'stable_diffusion_infinite_zoom',
3389
+ contextWindow: 0,
3390
+ tier: 'flagship',
3391
+ capabilities: new Set(['chat']),
3392
+ pricing: {},
3393
+ metadata: {
3394
+ owner: "arielreplicate",
3395
+ description: "Use Runway's Stable-diffusion inpainting model to create an infinite loop video",
3396
+ runCount: 38407,
3397
+ githubUrl: "https://github.com/ArielReplicate/stable-diffusion-infinite-zoom",
3398
+ visibility: "public",
3399
+ source: "replicate",
3400
+ latestVersionId: "a2527c5074fc0cf9fa6015a40d75d080d1ddf7082fabe142f1ccd882c18fce61",
3401
+ cogVersion: "0.4.4"
3402
+ }
3403
+ }, {
3404
+ id: 'arielreplicate/robust_video_matting',
3405
+ provider: 'replicate',
3406
+ name: 'robust_video_matting',
3407
+ contextWindow: 0,
3408
+ tier: 'flagship',
3409
+ capabilities: new Set(['chat']),
3410
+ pricing: {},
3411
+ metadata: {
3412
+ owner: "arielreplicate",
3413
+ description: "extract foreground of a video",
3414
+ runCount: 63785,
3415
+ githubUrl: "https://github.com/PeterL1n/RobustVideoMatting",
3416
+ visibility: "public",
3417
+ source: "replicate",
3418
+ latestVersionId: "73d2128a371922d5d1abf0712a1d974be0e4e2358cc1218e4e34714767232bac",
3419
+ cogVersion: "0.4.4"
3420
+ }
3421
+ }, {
3422
+ id: 'genmoai/mochi-1',
3423
+ provider: 'replicate',
3424
+ name: 'mochi-1',
3425
+ contextWindow: 0,
3426
+ tier: 'flagship',
3427
+ capabilities: new Set(['chat']),
3428
+ pricing: {},
3429
+ metadata: {
3430
+ owner: "genmoai",
3431
+ description: "Mochi 1 preview is an open video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation",
3432
+ runCount: 2975,
3433
+ githubUrl: "https://github.com/lucataco/cog-mochi-1",
3434
+ visibility: "public",
3435
+ source: "replicate",
3436
+ latestVersionId: "1944af04d098ef69bed7f9d335d102e652203f268ec4aaa2d836f6217217e460",
3437
+ cogVersion: "0.13.3"
3438
+ }
3439
+ }, {
3440
+ id: 'pollinations/real-basicvsr-video-superresolution',
3441
+ provider: 'replicate',
3442
+ name: 'real-basicvsr-video-superresolution',
3443
+ contextWindow: 0,
3444
+ tier: 'flagship',
3445
+ capabilities: new Set(['chat']),
3446
+ pricing: {},
3447
+ metadata: {
3448
+ owner: "pollinations",
3449
+ description: "RealBasicVSR: Investigating Tradeoffs in Real-World Video Super-Resolution",
3450
+ runCount: 9216,
3451
+ githubUrl: "https://github.com/pollinations/mmediting_video_superresolution",
3452
+ visibility: "public",
3453
+ source: "replicate",
3454
+ latestVersionId: "005b4db1d719c1672c522b220db3bc899a81889986b5adc7a01b4f4cfb34e4a7",
3455
+ cogVersion: "0.6.1"
3456
+ }
3457
+ }, {
3458
+ id: 'cjwbw/videocrafter',
3459
+ provider: 'replicate',
3460
+ name: 'videocrafter',
3461
+ contextWindow: 0,
3462
+ tier: 'flagship',
3463
+ capabilities: new Set(['chat']),
3464
+ pricing: {},
3465
+ metadata: {
3466
+ owner: "cjwbw",
3467
+ description: "VideoCrafter2: Text-to-Video and Image-to-Video Generation and Editing",
3468
+ runCount: 128374,
3469
+ githubUrl: "https://github.com/chenxwh/VideoCrafter",
3470
+ visibility: "public",
3471
+ source: "replicate",
3472
+ latestVersionId: "02edcff3e9d2d11dcc27e530773d988df25462b1ee93ed0257b6f246de4797c8",
3473
+ cogVersion: "0.9.4"
3474
+ }
3475
+ }, {
3476
+ id: 'zsxkib/animate-diff',
3477
+ provider: 'replicate',
3478
+ name: 'animate-diff',
3479
+ contextWindow: 0,
3480
+ tier: 'flagship',
3481
+ capabilities: new Set(['image']),
3482
+ pricing: {},
3483
+ metadata: {
3484
+ owner: "zsxkib",
3485
+ description: "🎨 AnimateDiff (w/ MotionLoRAs for Panning, Zooming, etc): Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning",
3486
+ runCount: 58819,
3487
+ githubUrl: "https://github.com/guoyww/AnimateDiff",
3488
+ visibility: "public",
3489
+ source: "replicate",
3490
+ latestVersionId: "269a616c8b0c2bbc12fc15fd51bb202b11e94ff0f7786c026aa905305c4ed9fb",
3491
+ cogVersion: "0.8.6"
3492
+ }
3493
+ }, {
3494
+ id: 'tencent/hunyuan-video',
3495
+ provider: 'replicate',
3496
+ name: 'hunyuan-video',
3497
+ contextWindow: 0,
3498
+ tier: 'flagship',
3499
+ capabilities: new Set(['chat']),
3500
+ pricing: {},
3501
+ metadata: {
3502
+ owner: "tencent",
3503
+ description: "A state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions",
3504
+ runCount: 114197,
3505
+ githubUrl: "https://github.com/zsxkib/HunyuanVideo/tree/replicate",
3506
+ visibility: "public",
3507
+ source: "replicate",
3508
+ latestVersionId: "6c9132aee14409cd6568d030453f1ba50f5f3412b844fe67f78a9eb62d55664f",
3509
+ cogVersion: "0.13.6"
3510
+ }
3511
+ }, {
3512
+ id: 'cuuupid/cogvideox-5b',
3513
+ provider: 'replicate',
3514
+ name: 'cogvideox-5b',
3515
+ contextWindow: 0,
3516
+ tier: 'flagship',
3517
+ capabilities: new Set(['chat']),
3518
+ pricing: {},
3519
+ metadata: {
3520
+ owner: "cuuupid",
3521
+ description: "Generate high quality videos from a prompt",
3522
+ runCount: 2360,
3523
+ githubUrl: "https://github.com/cuuupid/cog-cogvideox",
3524
+ visibility: "public",
3525
+ source: "replicate",
3526
+ latestVersionId: "5b14e2c2c648efecc8d36c6353576552f8a124e690587212f8e8bb17ecda3d8c",
3527
+ cogVersion: "v0.10.0-alpha13+dev"
3528
+ }
3529
+ }, {
3530
+ id: 'zsyoaoa/invsr',
3531
+ provider: 'replicate',
3532
+ name: 'invsr',
3533
+ contextWindow: 0,
3534
+ tier: 'flagship',
3535
+ capabilities: new Set(['chat']),
3536
+ pricing: {},
3537
+ metadata: {
3538
+ owner: "zsyoaoa",
3539
+ description: "Arbitrary-steps Image Super-resolution via Diffusion Inversion",
3540
+ runCount: 5095,
3541
+ githubUrl: "https://github.com/zsyOAOA/InvSR",
3542
+ visibility: "public",
3543
+ source: "replicate",
3544
+ latestVersionId: "37eebabfb6cdc4be2892b884b96b361d6fedc9f6a934d2fa3c1a2f85f004b0f0",
3545
+ cogVersion: "0.13.6"
3546
+ }
3547
+ }, {
3548
+ id: 'alexgenovese/upscaler',
3549
+ provider: 'replicate',
3550
+ name: 'upscaler',
3551
+ contextWindow: 0,
3552
+ tier: 'flagship',
3553
+ capabilities: new Set(['chat']),
3554
+ pricing: {},
3555
+ metadata: {
3556
+ owner: "alexgenovese",
3557
+ description: "GFPGAN aims at developing Practical Algorithms for Real-world Face and Object Restoration",
3558
+ runCount: 7141725,
3559
+ githubUrl: null,
3560
+ visibility: "public",
3561
+ source: "replicate",
3562
+ latestVersionId: "4f7eb3da655b5182e559d50a0437440f242992d47e5e20bd82829a79dee61ff3",
3563
+ cogVersion: "0.8.6"
3564
+ }
3565
+ }, {
3566
+ id: 'recraft-ai/recraft-creative-upscale',
3567
+ provider: 'replicate',
3568
+ name: 'recraft-creative-upscale',
3569
+ contextWindow: 0,
3570
+ tier: 'flagship',
3571
+ capabilities: new Set(['chat']),
3572
+ pricing: {},
3573
+ metadata: {
3574
+ owner: "recraft-ai",
3575
+ description: "Creative Upscale focuses on enhancing details and refining complex elements in the image. It doesn’t just increase resolution but adds depth by improving textures, fine details, and facial features.",
3576
+ runCount: 9194,
3577
+ githubUrl: null,
3578
+ visibility: "public",
3579
+ source: "replicate",
3580
+ latestVersionId: "bd741c666df240008994c1abdc24bbc08d41a1787631c381ed9d8b581915b22b",
3581
+ cogVersion: "0.16.8"
3582
+ }
3583
+ }, {
3584
+ id: 'recraft-ai/recraft-crisp-upscale',
3585
+ provider: 'replicate',
3586
+ name: 'recraft-crisp-upscale',
3587
+ contextWindow: 0,
3588
+ tier: 'flagship',
3589
+ capabilities: new Set(['chat']),
3590
+ pricing: {},
3591
+ metadata: {
3592
+ owner: "recraft-ai",
3593
+ description: "Designed to make images sharper and cleaner, Crisp Upscale increases overall quality, making visuals suitable for web use or print-ready materials.",
3594
+ runCount: 779341,
3595
+ githubUrl: null,
3596
+ visibility: "public",
3597
+ source: "replicate",
3598
+ latestVersionId: "cc8986968ffef15af08068dc39a686b5e8556de33f056a49c4019e03c1ccd3e0",
3599
+ cogVersion: "0.16.8"
3600
+ }
3601
+ }, {
3602
+ id: 'topazlabs/image-upscale',
3603
+ provider: 'replicate',
3604
+ name: 'image-upscale',
3605
+ contextWindow: 0,
3606
+ tier: 'flagship',
3607
+ capabilities: new Set(['chat']),
3608
+ pricing: {},
3609
+ metadata: {
3610
+ owner: "topazlabs",
3611
+ description: "Professional-grade image upscaling, from Topaz Labs",
3612
+ runCount: 863715,
3613
+ githubUrl: null,
3614
+ visibility: "public",
3615
+ source: "replicate",
3616
+ latestVersionId: "2fdc3b86a01d338ae89ad58e5d9241398a8a01de9b0dda41ba8a0434c8a00dc3",
3617
+ cogVersion: "0.14.4"
3618
+ }
3619
+ }, {
3620
+ id: 'philz1337x/crystal-upscaler',
3621
+ provider: 'replicate',
3622
+ name: 'crystal-upscaler',
3623
+ contextWindow: 0,
3624
+ tier: 'flagship',
3625
+ capabilities: new Set(['chat']),
3626
+ pricing: {},
3627
+ metadata: {
3628
+ owner: "philz1337x",
3629
+ description: "High-precision image upscaler optimized for portraeye and faces. One of the upscale modes powered by Clarity AI. X:https://x.com/philz1337x",
3630
+ runCount: 83409,
3631
+ githubUrl: null,
3632
+ visibility: "public",
3633
+ source: "replicate",
3634
+ latestVersionId: "7fd109216ec669863b67570b8db518931bcba4db2668543b1d4a0acc73a42d24",
3635
+ cogVersion: "0.16.8"
3636
+ }
3637
+ }, {
3638
+ id: 'google/upscaler',
3639
+ provider: 'replicate',
3640
+ name: 'upscaler',
3641
+ contextWindow: 0,
3642
+ tier: 'flagship',
3643
+ capabilities: new Set(['chat']),
3644
+ pricing: {},
3645
+ metadata: {
3646
+ owner: "google",
3647
+ description: "Upscale images 2x or 4x times",
3648
+ runCount: 45968,
3649
+ githubUrl: null,
3650
+ visibility: "public",
3651
+ source: "replicate",
3652
+ latestVersionId: "f0ba0b119dbad6408f1b062cbf01da490142c16590609b0097fdd888fd6e9449",
3653
+ cogVersion: "0.13.6"
3654
+ }
3655
+ }, {
3656
+ id: 'bria/increase-resolution',
3657
+ provider: 'replicate',
3658
+ name: 'increase-resolution',
3659
+ contextWindow: 0,
3660
+ tier: 'flagship',
3661
+ capabilities: new Set(['chat']),
3662
+ pricing: {},
3663
+ metadata: {
3664
+ owner: "bria",
3665
+ description: "Bria Increase resolution upscales the resolution of any image. It increases resolution using a dedicated upscaling method that preserves the original image content without regeneration.",
3666
+ runCount: 21062,
3667
+ githubUrl: null,
3668
+ visibility: "public",
3669
+ source: "replicate",
3670
+ latestVersionId: "8ae92c00caaeb3494107a34028d1ec1570a8d5b030c31f65140fe7d0333da1e4",
3671
+ cogVersion: "0.16.7"
3672
+ }
3673
+ }, {
3674
+ id: 'cjwbw/rudalle-sr',
3675
+ provider: 'replicate',
3676
+ name: 'rudalle-sr',
3677
+ contextWindow: 0,
3678
+ tier: 'flagship',
3679
+ capabilities: new Set(['image']),
3680
+ pricing: {},
3681
+ metadata: {
3682
+ owner: "cjwbw",
3683
+ description: "Real-ESRGAN super-resolution model from ruDALL-E",
3684
+ runCount: 484972,
3685
+ githubUrl: "https://github.com/CJWBW/rudalle-sr",
3686
+ visibility: "public",
3687
+ source: "replicate",
3688
+ latestVersionId: "32fdb2231d00a10d33754cc2ba794a2dfec94216579770785849ce6f149dbc69",
3689
+ cogVersion: "0.4.1"
3690
+ }
3691
+ }, {
3692
+ id: 'jingyunliang/swinir',
3693
+ provider: 'replicate',
3694
+ name: 'swinir',
3695
+ contextWindow: 0,
3696
+ tier: 'flagship',
3697
+ capabilities: new Set(['chat']),
3698
+ pricing: {},
3699
+ metadata: {
3700
+ owner: "jingyunliang",
3701
+ description: "Image Restoration Using Swin Transformer",
3702
+ runCount: 6124141,
3703
+ githubUrl: "https://github.com/JingyunLiang/SwinIR",
3704
+ visibility: "public",
3705
+ source: "replicate",
3706
+ latestVersionId: "660d922d33153019e8c263a3bba265de882e7f4f70396546b6c9c8f9d47a021a",
3707
+ cogVersion: "0.4.1"
3708
+ }
3709
+ }, {
3710
+ id: 'nightmareai/latent-sr',
3711
+ provider: 'replicate',
3712
+ name: 'latent-sr',
3713
+ contextWindow: 0,
3714
+ tier: 'flagship',
3715
+ capabilities: new Set(['chat']),
3716
+ pricing: {},
3717
+ metadata: {
3718
+ owner: "nightmareai",
3719
+ description: "Upscale images with the latent diffusion superresolution model",
3720
+ runCount: 116486,
3721
+ githubUrl: "https://github.com/NightmareAI/latent-diffusion",
3722
+ visibility: "public",
3723
+ source: "replicate",
3724
+ latestVersionId: "9117a98dd15e931011b8b960963a2dec20ab493c6c0d3a134525273da1616abc",
3725
+ cogVersion: "v0.3.13+dev"
3726
+ }
3727
+ }, {
3728
+ id: 'lucataco/controlnet-tile',
3729
+ provider: 'replicate',
3730
+ name: 'controlnet-tile',
3731
+ contextWindow: 0,
3732
+ tier: 'flagship',
3733
+ capabilities: new Set(['chat']),
3734
+ pricing: {},
3735
+ metadata: {
3736
+ owner: "lucataco",
3737
+ description: "Controlnet v1.1 - Tile Version",
3738
+ runCount: 4162,
3739
+ githubUrl: "https://github.com/lllyasviel/ControlNet",
3740
+ visibility: "public",
3741
+ source: "replicate",
3742
+ latestVersionId: "f688ff774c27a4843c819c9264c0f949925970bb278669ed9140364c8389869c",
3743
+ cogVersion: "0.8.6"
3744
+ }
3745
+ }, {
3746
+ id: 'lucataco/demofusion-enhance',
3747
+ provider: 'replicate',
3748
+ name: 'demofusion-enhance',
3749
+ contextWindow: 0,
3750
+ tier: 'flagship',
3751
+ capabilities: new Set(['chat']),
3752
+ pricing: {},
3753
+ metadata: {
3754
+ owner: "lucataco",
3755
+ description: "Image to Image enhancer using DemoFusion",
3756
+ runCount: 11095,
3757
+ githubUrl: "https://github.com/lucataco/cog-demofusion-enhance",
3758
+ visibility: "public",
3759
+ source: "replicate",
3760
+ latestVersionId: "5bcfe11066c820e8c08232c6efa3c8a7ab2cd667ad136ca173633f352170691e",
3761
+ cogVersion: "0.8.6"
3762
+ }
3763
+ }, {
3764
+ id: 'lucataco/stable-diffusion-x4-upscaler',
3765
+ provider: 'replicate',
3766
+ name: 'stable-diffusion-x4-upscaler',
3767
+ contextWindow: 0,
3768
+ tier: 'flagship',
3769
+ capabilities: new Set(['image']),
3770
+ pricing: {},
3771
+ metadata: {
3772
+ owner: "lucataco",
3773
+ description: "Stable Diffusion x4 upscaler model",
3774
+ runCount: 7697,
3775
+ githubUrl: "https://github.com/lucataco/cog-sd-x4-upscaler",
3776
+ visibility: "public",
3777
+ source: "replicate",
3778
+ latestVersionId: "c96e30cc409e6c5f68cd8b071b15fe819b23956669fd6461891000ee64545760",
3779
+ cogVersion: "0.8.6"
3780
+ }
3781
+ }, {
3782
+ id: 'cswry/seesr',
3783
+ provider: 'replicate',
3784
+ name: 'seesr',
3785
+ contextWindow: 0,
3786
+ tier: 'flagship',
3787
+ capabilities: new Set(['chat']),
3788
+ pricing: {},
3789
+ metadata: {
3790
+ owner: "cswry",
3791
+ description: "SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution",
3792
+ runCount: 101472,
3793
+ githubUrl: "https://github.com/lucataco/SeeSR",
3794
+ visibility: "public",
3795
+ source: "replicate",
3796
+ latestVersionId: "989cf3a66fd209363de347c3129d95d9fe639e44533ab47e07a6dfb3f250b6e3",
3797
+ cogVersion: "0.8.6"
3798
+ }
3799
+ }, {
3800
+ id: 'cjwbw/real-esrgan',
3801
+ provider: 'replicate',
3802
+ name: 'real-esrgan',
3803
+ contextWindow: 0,
3804
+ tier: 'flagship',
3805
+ capabilities: new Set(['chat']),
3806
+ pricing: {},
3807
+ metadata: {
3808
+ owner: "cjwbw",
3809
+ description: "Real-ESRGAN: Real-World Blind Super-Resolution",
3810
+ runCount: 2575444,
3811
+ githubUrl: "https://github.com/chenxwh/cog-Real-ESRGAN",
3812
+ visibility: "public",
3813
+ source: "replicate",
3814
+ latestVersionId: "d0ee3d708c9b911f122a4ad90046c5d26a0293b99476d697f6bb7f2e251ce2d4",
3815
+ cogVersion: "0.6.1"
3816
+ }
3817
+ }, {
3818
+ id: 'fermatresearch/high-resolution-controlnet-tile',
3819
+ provider: 'replicate',
3820
+ name: 'high-resolution-controlnet-tile',
3821
+ contextWindow: 0,
3822
+ tier: 'flagship',
3823
+ capabilities: new Set(['chat']),
3824
+ pricing: {},
3825
+ metadata: {
3826
+ owner: "fermatresearch",
3827
+ description: "UPDATE: new upscaling algorithm for a much improved image quality. Fermat.app open-source implementation of an efficient ControlNet 1.1 tile for high-quality upscales. Increase the creativity to encourage hallucination.",
3828
+ runCount: 645352,
3829
+ githubUrl: null,
3830
+ visibility: "public",
3831
+ source: "replicate",
3832
+ latestVersionId: "8e6a54d7b2848c48dc741a109d3fb0ea2a7f554eb4becd39a25cc532536ea975",
3833
+ cogVersion: "0.9.13"
3834
+ }
3835
+ }, {
3836
+ id: 'fermatresearch/magic-image-refiner',
3837
+ provider: 'replicate',
3838
+ name: 'magic-image-refiner',
3839
+ contextWindow: 0,
3840
+ tier: 'flagship',
3841
+ capabilities: new Set(['chat']),
3842
+ pricing: {},
3843
+ metadata: {
3844
+ owner: "fermatresearch",
3845
+ description: "A better alternative to SDXL refiners, providing a lot of quality and detail. Can also be used for inpainting or upscaling.",
3846
+ runCount: 946420,
3847
+ githubUrl: "https://github.com/BatouResearch/magic-image-refiner",
3848
+ visibility: "public",
3849
+ source: "replicate",
3850
+ latestVersionId: "507ddf6f977a7e30e46c0daefd30de7d563c72322f9e4cf7cbac52ef0f667b13",
3851
+ cogVersion: "0.8.6"
3852
+ }
3853
+ }, {
3854
+ id: 'zsxkib/aura-sr-v2',
3855
+ provider: 'replicate',
3856
+ name: 'aura-sr-v2',
3857
+ contextWindow: 0,
3858
+ tier: 'flagship',
3859
+ capabilities: new Set(['chat']),
3860
+ pricing: {},
3861
+ metadata: {
3862
+ owner: "zsxkib",
3863
+ description: "AuraSR v2: Second-gen GAN-based Super-Resolution for real-world applications",
3864
+ runCount: 15910,
3865
+ githubUrl: "https://github.com/zsxkib/cog-aura-sr-v2",
3866
+ visibility: "public",
3867
+ source: "replicate",
3868
+ latestVersionId: "5c137257cce8d5ce16e8a334b70e9e025106b5580affed0bc7d48940b594e74c",
3869
+ cogVersion: "0.9.14"
3870
+ }
3871
+ }, {
3872
+ id: 'nightmareai/real-esrgan',
3873
+ provider: 'replicate',
3874
+ name: 'real-esrgan',
3875
+ contextWindow: 0,
3876
+ tier: 'flagship',
3877
+ capabilities: new Set(['chat']),
3878
+ pricing: {},
3879
+ metadata: {
3880
+ owner: "nightmareai",
3881
+ description: "Real-ESRGAN with optional face correction and adjustable upscale",
3882
+ runCount: 76654148,
3883
+ githubUrl: "https://github.com/NightmareAI/Real-ESRGAN",
3884
+ visibility: "public",
3885
+ source: "replicate",
3886
+ latestVersionId: "b3ef194191d13140337468c916c2c5b96dd0cb06dffc032a022a31807f6a5ea8",
3887
+ cogVersion: "0.16.8"
3888
+ }
3889
+ }, {
3890
+ id: 'zsxkib/diffbir',
3891
+ provider: 'replicate',
3892
+ name: 'diffbir',
3893
+ contextWindow: 0,
3894
+ tier: 'flagship',
3895
+ capabilities: new Set(['chat']),
3896
+ pricing: {},
3897
+ metadata: {
3898
+ owner: "zsxkib",
3899
+ description: "✨DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior",
3900
+ runCount: 136779,
3901
+ githubUrl: "https://github.com/XPixelGroup/DiffBIR",
3902
+ visibility: "public",
3903
+ source: "replicate",
3904
+ latestVersionId: "51ed1464d8bbbaca811153b051d3b09ab42f0bdeb85804ae26ba323d7a66a4ac",
3905
+ cogVersion: "0.8.6"
3906
+ }
3907
+ }, {
3908
+ id: 'sczhou/codeformer',
3909
+ provider: 'replicate',
3910
+ name: 'codeformer',
3911
+ contextWindow: 0,
3912
+ tier: 'flagship',
3913
+ capabilities: new Set(['chat']),
3914
+ pricing: {},
3915
+ metadata: {
3916
+ owner: "sczhou",
3917
+ description: "Robust face restoration algorithm for old photos / AI-generated faces",
3918
+ runCount: 45792452,
3919
+ githubUrl: "https://github.com/sczhou/CodeFormer",
3920
+ visibility: "public",
3921
+ source: "replicate",
3922
+ latestVersionId: "cc4956dd26fa5a7185d5660cc9100fab1b8070a1d1654a8bb5eb6d443b020bb2",
3923
+ cogVersion: "0.8.5"
3924
+ }
3925
+ }, {
3926
+ id: 'juergengunz/ultimate-portrait-upscale',
3927
+ provider: 'replicate',
3928
+ name: 'ultimate-portrait-upscale',
3929
+ contextWindow: 0,
3930
+ tier: 'flagship',
3931
+ capabilities: new Set(['chat']),
3932
+ pricing: {},
3933
+ metadata: {
3934
+ owner: "juergengunz",
3935
+ description: "Upscale Portrait Images with ControlNet Tile",
3936
+ runCount: 49952,
3937
+ githubUrl: null,
3938
+ visibility: "public",
3939
+ source: "replicate",
3940
+ latestVersionId: "f7fdace4ec7adab7fa02688a160eee8057f070ead7fbb84e0904864fd2324be5",
3941
+ cogVersion: "0.8.6"
3942
+ }
3943
+ }, {
3944
+ id: 'lucataco/pasd-magnify',
3945
+ provider: 'replicate',
3946
+ name: 'pasd-magnify',
3947
+ contextWindow: 0,
3948
+ tier: 'flagship',
3949
+ capabilities: new Set(['chat']),
3950
+ pricing: {},
3951
+ metadata: {
3952
+ owner: "lucataco",
3953
+ description: "(Academic and Non-commercial use only) Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization",
3954
+ runCount: 42373,
3955
+ githubUrl: "https://github.com/lucataco/cog-PASD-Magnify",
3956
+ visibility: "public",
3957
+ source: "replicate",
3958
+ latestVersionId: "d59e83ee13c42b137aee558c483e3acc0a8ecdacb1444a7be48152f008dcc195",
3959
+ cogVersion: "0.8.6"
3960
+ }
3961
+ }, {
3962
+ id: 'cjwbw/supir',
3963
+ provider: 'replicate',
3964
+ name: 'supir',
3965
+ contextWindow: 0,
3966
+ tier: 'flagship',
3967
+ capabilities: new Set(['chat']),
3968
+ pricing: {},
3969
+ metadata: {
3970
+ owner: "cjwbw",
3971
+ description: "Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This version uses LLaVA-13b for captioning.",
3972
+ runCount: 189536,
3973
+ githubUrl: "https://github.com/chenxwh/SUPIR",
3974
+ visibility: "public",
3975
+ source: "replicate",
3976
+ latestVersionId: "1302b550b4f7681da87ed0e405016d443fe1fafd64dabce6673401855a5039b5",
3977
+ cogVersion: "0.9.4"
3978
+ }
3979
+ }, {
3980
+ id: 'zsxkib/aura-sr',
3981
+ provider: 'replicate',
3982
+ name: 'aura-sr',
3983
+ contextWindow: 0,
3984
+ tier: 'flagship',
3985
+ capabilities: new Set(['chat']),
3986
+ pricing: {},
3987
+ metadata: {
3988
+ owner: "zsxkib",
3989
+ description: "AuraSR: GAN-based Super-Resolution for real-world",
3990
+ runCount: 3140,
3991
+ githubUrl: "https://github.com/zsxkib/cog-aura-sr",
3992
+ visibility: "public",
3993
+ source: "replicate",
3994
+ latestVersionId: "7231d40ac06e74c6d1bc287309c396fa4791e4cf4fdcb91fb4b191c6c485fc1c",
3995
+ cogVersion: "0.9.9"
3996
+ }
3997
+ }, {
3998
+ id: 'xinntao/esrgan',
3999
+ provider: 'replicate',
4000
+ name: 'esrgan',
4001
+ contextWindow: 0,
4002
+ tier: 'flagship',
4003
+ capabilities: new Set(['chat']),
4004
+ pricing: {},
4005
+ metadata: {
4006
+ owner: "xinntao",
4007
+ description: "Image 4x super-resolution",
4008
+ runCount: 155200,
4009
+ githubUrl: "https://github.com/xinntao/ESRGAN",
4010
+ visibility: "public",
4011
+ source: "replicate",
4012
+ latestVersionId: "c263265e04b16fda1046d1828997fc27b46610647a3348df1c72fbffbdbac912",
4013
+ cogVersion: "0.4.1"
4014
+ }
4015
+ }, {
4016
+ id: 'jingyunliang/hcflow-sr',
4017
+ provider: 'replicate',
4018
+ name: 'hcflow-sr',
4019
+ contextWindow: 0,
4020
+ tier: 'flagship',
4021
+ capabilities: new Set(['chat']),
4022
+ pricing: {},
4023
+ metadata: {
4024
+ owner: "jingyunliang",
4025
+ description: "Image Super-Resolution",
4026
+ runCount: 222821,
4027
+ githubUrl: "https://github.com/JingyunLiang/HCFlow",
4028
+ visibility: "public",
4029
+ source: "replicate",
4030
+ latestVersionId: "567785261e974455ede3b0644d1d7e5aa8d9e40a22217a8726900acdcd9e19ce",
4031
+ cogVersion: "0.4.1"
4032
+ }
4033
+ }, {
4034
+ id: 'fewjative/ultimate-sd-upscale',
4035
+ provider: 'replicate',
4036
+ name: 'ultimate-sd-upscale',
4037
+ contextWindow: 0,
4038
+ tier: 'flagship',
4039
+ capabilities: new Set(['chat']),
4040
+ pricing: {},
4041
+ metadata: {
4042
+ owner: "fewjative",
4043
+ description: "Ultimate SD Upscale with ControlNet Tile",
4044
+ runCount: 164374,
4045
+ githubUrl: "https://github.com/fewjative/cog-ultimate-sd-upscale",
4046
+ visibility: "public",
4047
+ source: "replicate",
4048
+ latestVersionId: "5daf1012d946160622cd1bd45ed8f12d9675d24659276ccfe24804035f3b3ad7",
4049
+ cogVersion: "0.8.6"
4050
+ }
4051
+ }, {
4052
+ id: 'mv-lab/swin2sr',
4053
+ provider: 'replicate',
4054
+ name: 'swin2sr',
4055
+ contextWindow: 0,
4056
+ tier: 'flagship',
4057
+ capabilities: new Set(['chat']),
4058
+ pricing: {},
4059
+ metadata: {
4060
+ owner: "mv-lab",
4061
+ description: "3 Million Runs! AI Photorealistic Image Super-Resolution and Restoration",
4062
+ runCount: 3573115,
4063
+ githubUrl: "https://github.com/mv-lab/swin2sr",
4064
+ visibility: "public",
4065
+ source: "replicate",
4066
+ latestVersionId: "a01b0512004918ca55d02e554914a9eca63909fa83a29ff0f115c78a7045574f",
4067
+ cogVersion: "0.4.4"
4068
+ }
4069
+ }, {
4070
+ id: 'tencentarc/gfpgan',
4071
+ provider: 'replicate',
4072
+ name: 'gfpgan',
4073
+ contextWindow: 0,
4074
+ tier: 'flagship',
4075
+ capabilities: new Set(['chat']),
4076
+ pricing: {},
4077
+ metadata: {
4078
+ owner: "tencentarc",
4079
+ description: "Practical face restoration algorithm for *old photos* or *AI-generated faces*",
4080
+ runCount: 98747433,
4081
+ githubUrl: "https://github.com/replicate/GFPGAN",
4082
+ visibility: "public",
4083
+ source: "replicate",
4084
+ latestVersionId: "0fbacf7afc6c144e5be9767cff80f25aff23e52b0708f17e20f9879b2f21516c",
4085
+ cogVersion: "0.4.2"
4086
+ }
4087
+ }, {
4088
+ id: 'philz1337x/clarity-upscaler',
4089
+ provider: 'replicate',
4090
+ name: 'clarity-upscaler',
4091
+ contextWindow: 0,
4092
+ tier: 'flagship',
4093
+ capabilities: new Set(['chat']),
4094
+ pricing: {},
4095
+ metadata: {
4096
+ owner: "philz1337x",
4097
+ description: "High resolution image Upscaler and Enhancer. Use at ClarityAI.co. A free Magnific alternative. Twitter/X: @philz1337x",
4098
+ runCount: 22100084,
4099
+ githubUrl: "https://github.com/philz1337x/clarity-upscaler",
4100
+ visibility: "public",
4101
+ source: "replicate",
4102
+ latestVersionId: "dfad41707589d68ecdccd1dfa600d55a208f9310748e44bfe35b4a6291453d5e",
4103
+ cogVersion: "0.8.0-beta11"
4104
+ }
4105
+ }];
4106
+ //# sourceMappingURL=replicate.js.map