fal-endpoint-types 1.3.34 → 1.3.36

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.
@@ -91,11 +91,11 @@ export interface XaiGrokImagineVideoTextToVideoOutput {
91
91
  * "height": 720,
92
92
  * "duration": 6.041667,
93
93
  * "url": "https://v3b.fal.media/files/b/0a8b90e4/RUAbFYlssdqnbjNLmE8qP_IX7BNYGP.mp4",
94
- * "width": 1280,
95
94
  * "fps": 24,
95
+ * "width": 1280,
96
96
  * "file_name": "RUAbFYlssdqnbjNLmE8qP_IX7BNYGP.mp4",
97
- * "content_type": "video/mp4",
98
- * "num_frames": 145
97
+ * "num_frames": 145,
98
+ * "content_type": "video/mp4"
99
99
  * }
100
100
  */
101
101
  video: Components.VideoFile;
@@ -142,11 +142,11 @@ export interface XaiGrokImagineVideoImageToVideoOutput {
142
142
  * "height": 720,
143
143
  * "duration": 6.041667,
144
144
  * "url": "https://v3b.fal.media/files/b/0a8b90e0/0Ci1dviuSnEyUZzBUq-_5_nu7MrAAa.mp4",
145
- * "width": 1280,
146
145
  * "fps": 24,
146
+ * "width": 1280,
147
147
  * "file_name": "0Ci1dviuSnEyUZzBUq-_5_nu7MrAAa.mp4",
148
- * "content_type": "video/mp4",
149
- * "num_frames": 145
148
+ * "num_frames": 145,
149
+ * "content_type": "video/mp4"
150
150
  * }
151
151
  */
152
152
  video: Components.VideoFile;
@@ -181,11 +181,11 @@ export interface XaiGrokImagineVideoEditVideoOutput {
181
181
  * "height": 720,
182
182
  * "duration": 5.041667,
183
183
  * "url": "https://v3b.fal.media/files/b/0a8b9113/EuDrZuQTW9m1phBXOsauz_EpJH3s8X.mp4",
184
- * "width": 1280,
185
184
  * "fps": 24,
185
+ * "width": 1280,
186
186
  * "file_name": "EuDrZuQTW9m1phBXOsauz_EpJH3s8X.mp4",
187
- * "content_type": "video/mp4",
188
- * "num_frames": 121
187
+ * "num_frames": 121,
188
+ * "content_type": "video/mp4"
189
189
  * }
190
190
  */
191
191
  video: Components.VideoFile;
@@ -1582,6 +1582,38 @@ export interface SharedType_fe5 {
1582
1582
  };
1583
1583
  }
1584
1584
 
1585
+ export interface SharedType_fda {
1586
+ /**
1587
+ * Masks
1588
+ * @description Dictionary of label: mask image
1589
+ * @example [
1590
+ * {
1591
+ * "height": 1200,
1592
+ * "file_size": 15724,
1593
+ * "file_name": "019c3c1e3c50446e9996f709d36debb4.png",
1594
+ * "content_type": "image/png",
1595
+ * "url": "https://v3.fal.media/files/monkey/6ITmhHQJ-69s-UxajrY5T_019c3c1e3c50446e9996f709d36debb4.png",
1596
+ * "width": 1800
1597
+ * },
1598
+ * {
1599
+ * "height": 1200,
1600
+ * "file_size": 14905,
1601
+ * "file_name": "0a1522ca410942c7ad6c73efa15b3549.png",
1602
+ * "content_type": "image/png",
1603
+ * "url": "https://v3.fal.media/files/monkey/IljtMxahoo9-7SUpx0fth_0a1522ca410942c7ad6c73efa15b3549.png",
1604
+ * "width": 1800
1605
+ * }
1606
+ * ]
1607
+ */
1608
+ masks: Components.Image[];
1609
+ /**
1610
+ * Output
1611
+ * @description Generated output
1612
+ * @example <p> A white pickup truck </p> [SEG] is parked on the side of <p> the red building </p> [SEG] , creating a unique and eye-catching contrast.<|im_end|>
1613
+ */
1614
+ output: string;
1615
+ }
1616
+
1585
1617
  export interface SharedType_fd1 {
1586
1618
  /**
1587
1619
  * @description The generated video
@@ -1854,13 +1886,6 @@ export interface SharedType_faf {
1854
1886
  sync_mode?: boolean;
1855
1887
  }
1856
1888
 
1857
- export interface SharedType_f7a {
1858
- config_file: Components.File;
1859
- debug_dataset?: Components.File;
1860
- lora_file: Components.File;
1861
- video?: Components.File;
1862
- }
1863
-
1864
1889
  export interface SharedType_f67 {
1865
1890
  /**
1866
1891
  * Auto Trim
@@ -2616,14 +2641,6 @@ export interface SharedType_e4b {
2616
2641
  steps?: number;
2617
2642
  }
2618
2643
 
2619
- export interface SharedType_e43 {
2620
- /**
2621
- * Image
2622
- * @description The generated image file info.
2623
- */
2624
- image: Components.Image_2;
2625
- }
2626
-
2627
2644
  export interface SharedType_e33 {
2628
2645
  /**
2629
2646
  * Has Nsfw Concepts
@@ -2659,6 +2676,29 @@ export interface SharedType_e33 {
2659
2676
  };
2660
2677
  }
2661
2678
 
2679
+ export interface SharedType_e19 {
2680
+ /**
2681
+ * Images
2682
+ * @description The generated images
2683
+ * @example [
2684
+ * {
2685
+ * "height": 1536,
2686
+ * "file_size": 3731290,
2687
+ * "file_name": "257cf8e7bd3a47c2959396343d5b38cf.png",
2688
+ * "content_type": "image/png",
2689
+ * "url": "https://v3.fal.media/files/tiger/48e63e0K6C9XQYBuomoU-_257cf8e7bd3a47c2959396343d5b38cf.png",
2690
+ * "width": 1536
2691
+ * }
2692
+ * ]
2693
+ */
2694
+ images: Components.Image[];
2695
+ /**
2696
+ * Seed
2697
+ * @description Seed value used for generation.
2698
+ */
2699
+ seed: number;
2700
+ }
2701
+
2662
2702
  export interface SharedType_e18 {
2663
2703
  /**
2664
2704
  * Default Caption
@@ -3880,33 +3920,24 @@ export interface SharedType_cbd {
3880
3920
  sync_mode?: boolean;
3881
3921
  }
3882
3922
 
3883
- export interface SharedType_cb6 {
3923
+ export interface SharedType_cbb {
3884
3924
  /**
3885
- * Prompt
3886
- * @description The prompt used for the generation.
3887
- * @example A woman stands still amid a busy neon-lit street at night. The camera slowly dollies in toward her face as people blur past, their motion emphasizing her calm presence. City lights flicker and reflections shift across her denim jacket.
3888
- */
3889
- prompt: string;
3890
- /**
3891
- * Seed
3892
- * @description The seed used for the random number generator.
3893
- * @example 2078003885
3925
+ * Output
3926
+ * @description Generated output from video processing
3927
+ * @example that's the way I look at it and I don't know what you would say. Sooner or later the child gets run over.
3928
+ * They seem to be too local, too provincial.
3894
3929
  */
3895
- seed: number;
3930
+ output: string;
3896
3931
  /**
3897
- * @description The generated video.
3932
+ * @description Token usage information
3898
3933
  * @example {
3899
- * "height": 704,
3900
- * "duration": 6.44,
3901
- * "url": "https://v3b.fal.media/files/b/0a894013/N9lnMTq7W3uMC0lOQg845_BknRPV8I.mp4",
3902
- * "fps": 25,
3903
- * "width": 1248,
3904
- * "file_name": "CJcQGDrxOSRg2YFl5GNDt_glXPMoji.mp4",
3905
- * "num_frames": 161,
3906
- * "content_type": "video/mp4"
3934
+ * "completion_tokens": 100,
3935
+ * "total_tokens": 1100,
3936
+ * "prompt_tokens": 1000,
3937
+ * "cost": 0.0005
3907
3938
  * }
3908
3939
  */
3909
- video: Components.VideoFile;
3940
+ usage: Components.UsageInfo;
3910
3941
  }
3911
3942
 
3912
3943
  export interface SharedType_cb4 {
@@ -5230,29 +5261,6 @@ export interface SharedType_a9b {
5230
5261
  seed?: number;
5231
5262
  }
5232
5263
 
5233
- export interface SharedType_a97 {
5234
- /**
5235
- * Images
5236
- * @description The generated images
5237
- * @example [
5238
- * {
5239
- * "file_size": 3731290,
5240
- * "height": 1536,
5241
- * "file_name": "257cf8e7bd3a47c2959396343d5b38cf.png",
5242
- * "content_type": "image/png",
5243
- * "url": "https://v3.fal.media/files/tiger/48e63e0K6C9XQYBuomoU-_257cf8e7bd3a47c2959396343d5b38cf.png",
5244
- * "width": 1536
5245
- * }
5246
- * ]
5247
- */
5248
- images: Components.Image[];
5249
- /**
5250
- * Seed
5251
- * @description Seed value used for generation.
5252
- */
5253
- seed: number;
5254
- }
5255
-
5256
5264
  export interface SharedType_a8f {
5257
5265
  /**
5258
5266
  * Image Url
@@ -6808,6 +6816,26 @@ export interface SharedType_8b9 {
6808
6816
  video: Components.VideoFile;
6809
6817
  }
6810
6818
 
6819
+ export interface SharedType_8b7 {
6820
+ /**
6821
+ * Image Url
6822
+ * @description The URL of the image to be processed.
6823
+ * @example https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg
6824
+ * @example http://ecx.images-amazon.com/images/I/51UUzBDAMsL.jpg
6825
+ */
6826
+ image_url: string;
6827
+ /**
6828
+ * @description The user input coordinates
6829
+ * @example {
6830
+ * "y1": 100,
6831
+ * "x2": 200,
6832
+ * "y2": 200,
6833
+ * "x1": 100
6834
+ * }
6835
+ */
6836
+ region: Components.Region;
6837
+ }
6838
+
6811
6839
  export interface SharedType_8a3 {
6812
6840
  /**
6813
6841
  * @description The generated video
@@ -7023,35 +7051,6 @@ export interface SharedType_85d {
7023
7051
  sync_mode?: boolean;
7024
7052
  }
7025
7053
 
7026
- export interface SharedType_857 {
7027
- /**
7028
- * Prompt
7029
- * @description The prompt used for the generation.
7030
- * @example A cowboy walking through a dusty town at high noon, camera following from behind, cinematic depth, realistic lighting, western mood, 4K film grain.
7031
- */
7032
- prompt: string;
7033
- /**
7034
- * Seed
7035
- * @description The seed used for the random number generator.
7036
- * @example 149063119
7037
- */
7038
- seed: number;
7039
- /**
7040
- * @description The generated video.
7041
- * @example {
7042
- * "height": 704,
7043
- * "duration": 6.44,
7044
- * "url": "https://v3b.fal.media/files/b/0a8824b1/sdm0KfmenrlywesfzY1Y1_if6euPp1.mp4",
7045
- * "fps": 25,
7046
- * "width": 1248,
7047
- * "file_name": "sdm0KfmenrlywesfzY1Y1_if6euPp1.mp4",
7048
- * "num_frames": 161,
7049
- * "content_type": "video/mp4"
7050
- * }
7051
- */
7052
- video: Components.VideoFile;
7053
- }
7054
-
7055
7054
  export interface SharedType_844 {
7056
7055
  /**
7057
7056
  * Prompt
@@ -8355,6 +8354,35 @@ export interface SharedType_709 {
8355
8354
  video_url: string;
8356
8355
  }
8357
8356
 
8357
+ export interface SharedType_6ef {
8358
+ /**
8359
+ * Prompt
8360
+ * @description The prompt used for the generation.
8361
+ * @example A cowboy walking through a dusty town at high noon, camera following from behind, cinematic depth, realistic lighting, western mood, 4K film grain.
8362
+ */
8363
+ prompt: string;
8364
+ /**
8365
+ * Seed
8366
+ * @description The seed used for the random number generator.
8367
+ * @example 149063119
8368
+ */
8369
+ seed: number;
8370
+ /**
8371
+ * @description The generated video.
8372
+ * @example {
8373
+ * "height": 704,
8374
+ * "duration": 6.44,
8375
+ * "url": "https://v3b.fal.media/files/b/0a8824b1/sdm0KfmenrlywesfzY1Y1_if6euPp1.mp4",
8376
+ * "width": 1248,
8377
+ * "fps": 25,
8378
+ * "file_name": "sdm0KfmenrlywesfzY1Y1_if6euPp1.mp4",
8379
+ * "content_type": "video/mp4",
8380
+ * "num_frames": 161
8381
+ * }
8382
+ */
8383
+ video: Components.VideoFile;
8384
+ }
8385
+
8358
8386
  export interface SharedType_6cd {
8359
8387
  /**
8360
8388
  * Aspect Ratio
@@ -8654,26 +8682,6 @@ export interface SharedType_678 {
8654
8682
  seed: number;
8655
8683
  }
8656
8684
 
8657
- export interface SharedType_676 {
8658
- /**
8659
- * Output
8660
- * @description Generated output from video processing
8661
- * @example that's the way I look at it and I don't know what you would say. Sooner or later the child gets run over.
8662
- * They seem to be too local, too provincial.
8663
- */
8664
- output: string;
8665
- /**
8666
- * @description Token usage information
8667
- * @example {
8668
- * "prompt_tokens": 1000,
8669
- * "total_tokens": 1100,
8670
- * "completion_tokens": 100,
8671
- * "cost": 0.0005
8672
- * }
8673
- */
8674
- usage: Components.UsageInfo;
8675
- }
8676
-
8677
8685
  export interface SharedType_6711 {
8678
8686
  /**
8679
8687
  * Prompt
@@ -9116,6 +9124,35 @@ export interface SharedType_5f1 {
9116
9124
  };
9117
9125
  }
9118
9126
 
9127
+ export interface SharedType_5db {
9128
+ /**
9129
+ * Prompt
9130
+ * @description The prompt used for the generation.
9131
+ * @example A woman stands still amid a busy neon-lit street at night. The camera slowly dollies in toward her face as people blur past, their motion emphasizing her calm presence. City lights flicker and reflections shift across her denim jacket.
9132
+ */
9133
+ prompt: string;
9134
+ /**
9135
+ * Seed
9136
+ * @description The seed used for the random number generator.
9137
+ * @example 2078003885
9138
+ */
9139
+ seed: number;
9140
+ /**
9141
+ * @description The generated video.
9142
+ * @example {
9143
+ * "height": 704,
9144
+ * "duration": 6.44,
9145
+ * "url": "https://v3b.fal.media/files/b/0a894013/N9lnMTq7W3uMC0lOQg845_BknRPV8I.mp4",
9146
+ * "width": 1248,
9147
+ * "fps": 25,
9148
+ * "file_name": "CJcQGDrxOSRg2YFl5GNDt_glXPMoji.mp4",
9149
+ * "content_type": "video/mp4",
9150
+ * "num_frames": 161
9151
+ * }
9152
+ */
9153
+ video: Components.VideoFile;
9154
+ }
9155
+
9119
9156
  export interface SharedType_5ac {
9120
9157
  /**
9121
9158
  * Acoustic Cfg Scale
@@ -11052,6 +11089,35 @@ export interface SharedType_43e {
11052
11089
  image: Components.Image_2;
11053
11090
  }
11054
11091
 
11092
+ export interface SharedType_437 {
11093
+ /**
11094
+ * Prompt
11095
+ * @description The prompt used for the generation.
11096
+ * @example Continue the scene naturally, maintaining the same style and motion.
11097
+ */
11098
+ prompt: string;
11099
+ /**
11100
+ * Seed
11101
+ * @description The seed used for the random number generator.
11102
+ * @example 866232447
11103
+ */
11104
+ seed: number;
11105
+ /**
11106
+ * @description The generated video.
11107
+ * @example {
11108
+ * "height": 704,
11109
+ * "duration": 10.28,
11110
+ * "url": "https://v3b.fal.media/files/b/0a88289e/CJcQGDrxOSRg2YFl5GNDt_glXPMoji.mp4",
11111
+ * "width": 1248,
11112
+ * "fps": 25,
11113
+ * "file_name": "CJcQGDrxOSRg2YFl5GNDt_glXPMoji.mp4",
11114
+ * "content_type": "video/mp4",
11115
+ * "num_frames": 257
11116
+ * }
11117
+ */
11118
+ video: Components.VideoFile;
11119
+ }
11120
+
11055
11121
  export interface SharedType_411 {
11056
11122
  /**
11057
11123
  * Aspect Ratio
@@ -11150,35 +11216,6 @@ export interface SharedType_3be {
11150
11216
  video: Components.File;
11151
11217
  }
11152
11218
 
11153
- export interface SharedType_3b0 {
11154
- /**
11155
- * Prompt
11156
- * @description The prompt used for the generation.
11157
- * @example black-and-white video, a cowboy walks through a dusty town, film grain
11158
- */
11159
- prompt: string;
11160
- /**
11161
- * Seed
11162
- * @description The seed used for the random number generator.
11163
- * @example 1490631192028410600
11164
- */
11165
- seed: number;
11166
- /**
11167
- * @description The generated video.
11168
- * @example {
11169
- * "height": 704,
11170
- * "duration": 6.44,
11171
- * "url": "https://v3b.fal.media/files/b/0a895ed5/SaTGe87IpMUMiSq33w5Qb_RoCJFZhc.mp4",
11172
- * "fps": 25,
11173
- * "width": 1248,
11174
- * "file_name": "SaTGe87IpMUMiSq33w5Qb_RoCJFZhc.mp4",
11175
- * "num_frames": 161,
11176
- * "content_type": "video/mp4"
11177
- * }
11178
- */
11179
- video: Components.VideoFile;
11180
- }
11181
-
11182
11219
  export interface SharedType_397 {
11183
11220
  /**
11184
11221
  * Acceleration
@@ -11499,35 +11536,6 @@ export interface SharedType_371 {
11499
11536
  prompt_optimizer?: boolean;
11500
11537
  }
11501
11538
 
11502
- export interface SharedType_369 {
11503
- /**
11504
- * Prompt
11505
- * @description The prompt used for the generation.
11506
- * @example Continue the scene naturally, maintaining the same style and motion.
11507
- */
11508
- prompt: string;
11509
- /**
11510
- * Seed
11511
- * @description The seed used for the random number generator.
11512
- * @example 866232447
11513
- */
11514
- seed: number;
11515
- /**
11516
- * @description The generated video.
11517
- * @example {
11518
- * "height": 704,
11519
- * "duration": 10.28,
11520
- * "url": "https://v3b.fal.media/files/b/0a88289e/CJcQGDrxOSRg2YFl5GNDt_glXPMoji.mp4",
11521
- * "fps": 25,
11522
- * "width": 1248,
11523
- * "file_name": "CJcQGDrxOSRg2YFl5GNDt_glXPMoji.mp4",
11524
- * "num_frames": 257,
11525
- * "content_type": "video/mp4"
11526
- * }
11527
- */
11528
- video: Components.VideoFile;
11529
- }
11530
-
11531
11539
  export interface SharedType_367 {
11532
11540
  /**
11533
11541
  * Aspect Ratio
@@ -11737,26 +11745,6 @@ export interface SharedType_304 {
11737
11745
  voice: Components.TextVoice;
11738
11746
  }
11739
11747
 
11740
- export interface SharedType_2ff {
11741
- /**
11742
- * Image Url
11743
- * @description The URL of the image to be processed.
11744
- * @example https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg
11745
- * @example http://ecx.images-amazon.com/images/I/51UUzBDAMsL.jpg
11746
- */
11747
- image_url: string;
11748
- /**
11749
- * @description The user input coordinates
11750
- * @example {
11751
- * "y2": 200,
11752
- * "x2": 200,
11753
- * "x1": 100,
11754
- * "y1": 100
11755
- * }
11756
- */
11757
- region: Components.Region;
11758
- }
11759
-
11760
11748
  export interface SharedType_2e6 {
11761
11749
  /**
11762
11750
  * Aspect Ratio
@@ -12536,6 +12524,35 @@ export interface SharedType_20d {
12536
12524
  seed: number;
12537
12525
  }
12538
12526
 
12527
+ export interface SharedType_1f5 {
12528
+ /**
12529
+ * Prompt
12530
+ * @description The prompt used for the generation.
12531
+ * @example black-and-white video, a cowboy walks through a dusty town, film grain
12532
+ */
12533
+ prompt: string;
12534
+ /**
12535
+ * Seed
12536
+ * @description The seed used for the random number generator.
12537
+ * @example 1490631192028410600
12538
+ */
12539
+ seed: number;
12540
+ /**
12541
+ * @description The generated video.
12542
+ * @example {
12543
+ * "height": 704,
12544
+ * "duration": 6.44,
12545
+ * "url": "https://v3b.fal.media/files/b/0a895ed5/SaTGe87IpMUMiSq33w5Qb_RoCJFZhc.mp4",
12546
+ * "width": 1248,
12547
+ * "fps": 25,
12548
+ * "file_name": "SaTGe87IpMUMiSq33w5Qb_RoCJFZhc.mp4",
12549
+ * "content_type": "video/mp4",
12550
+ * "num_frames": 161
12551
+ * }
12552
+ */
12553
+ video: Components.VideoFile;
12554
+ }
12555
+
12539
12556
  export interface SharedType_1eb {
12540
12557
  /**
12541
12558
  * @description The generated video file.
@@ -13156,7 +13173,7 @@ export interface SharedType_129 {
13156
13173
  results: string;
13157
13174
  }
13158
13175
 
13159
- export interface SharedType_1001 {
13176
+ export interface SharedType_100 {
13160
13177
  /**
13161
13178
  * Prompt
13162
13179
  * @description The prompt used for generating the video.
@@ -13174,38 +13191,6 @@ export interface SharedType_1001 {
13174
13191
  video: Components.File;
13175
13192
  }
13176
13193
 
13177
- export interface SharedType_100 {
13178
- /**
13179
- * Masks
13180
- * @description Dictionary of label: mask image
13181
- * @example [
13182
- * {
13183
- * "file_size": 15724,
13184
- * "height": 1200,
13185
- * "file_name": "019c3c1e3c50446e9996f709d36debb4.png",
13186
- * "content_type": "image/png",
13187
- * "url": "https://v3.fal.media/files/monkey/6ITmhHQJ-69s-UxajrY5T_019c3c1e3c50446e9996f709d36debb4.png",
13188
- * "width": 1800
13189
- * },
13190
- * {
13191
- * "file_size": 14905,
13192
- * "height": 1200,
13193
- * "file_name": "0a1522ca410942c7ad6c73efa15b3549.png",
13194
- * "content_type": "image/png",
13195
- * "url": "https://v3.fal.media/files/monkey/IljtMxahoo9-7SUpx0fth_0a1522ca410942c7ad6c73efa15b3549.png",
13196
- * "width": 1800
13197
- * }
13198
- * ]
13199
- */
13200
- masks: Components.Image[];
13201
- /**
13202
- * Output
13203
- * @description Generated output
13204
- * @example <p> A white pickup truck </p> [SEG] is parked on the side of <p> the red building </p> [SEG] , creating a unique and eye-catching contrast.<|im_end|>
13205
- */
13206
- output: string;
13207
- }
13208
-
13209
13194
  export interface SharedType_0ff {
13210
13195
  /**
13211
13196
  * @description The generated speaker embedding file in safetensors format.
@@ -14679,9 +14664,9 @@ export interface OpenrouterRouterVisionOutput {
14679
14664
  /**
14680
14665
  * @description Token usage information
14681
14666
  * @example {
14682
- * "prompt_tokens": 1340,
14683
- * "total_tokens": 1403,
14684
14667
  * "completion_tokens": 63,
14668
+ * "total_tokens": 1403,
14669
+ * "prompt_tokens": 1340,
14685
14670
  * "cost": 0.0005595
14686
14671
  * }
14687
14672
  */
@@ -14745,7 +14730,7 @@ export interface OpenrouterRouterVideoEnterpriseInput {
14745
14730
  video_urls?: string[];
14746
14731
  }
14747
14732
 
14748
- export interface OpenrouterRouterVideoEnterpriseOutput extends SharedType_676 {}
14733
+ export interface OpenrouterRouterVideoEnterpriseOutput extends SharedType_cbb {}
14749
14734
 
14750
14735
  export interface OpenrouterRouterVideoInput {
14751
14736
  /**
@@ -14797,7 +14782,7 @@ export interface OpenrouterRouterVideoInput {
14797
14782
  video_urls?: string[];
14798
14783
  }
14799
14784
 
14800
- export interface OpenrouterRouterVideoOutput extends SharedType_676 {}
14785
+ export interface OpenrouterRouterVideoOutput extends SharedType_cbb {}
14801
14786
 
14802
14787
  export interface OpenrouterRouterAudioInput {
14803
14788
  /**
@@ -14856,9 +14841,9 @@ export interface OpenrouterRouterAudioOutput {
14856
14841
  /**
14857
14842
  * @description Token usage information
14858
14843
  * @example {
14859
- * "prompt_tokens": 500,
14860
- * "total_tokens": 550,
14861
14844
  * "completion_tokens": 50,
14845
+ * "total_tokens": 550,
14846
+ * "prompt_tokens": 500,
14862
14847
  * "cost": 0.0003
14863
14848
  * }
14864
14849
  */
@@ -14940,9 +14925,9 @@ export interface OpenrouterRouterOutput {
14940
14925
  /**
14941
14926
  * @description Token usage information
14942
14927
  * @example {
14943
- * "prompt_tokens": 40,
14944
- * "total_tokens": 267,
14945
14928
  * "completion_tokens": 227,
14929
+ * "total_tokens": 267,
14930
+ * "prompt_tokens": 40,
14946
14931
  * "cost": 0.0005795
14947
14932
  * }
14948
14933
  */
@@ -15357,7 +15342,7 @@ export interface ZImageTurboTilingLoraInput {
15357
15342
  enable_safety_checker?: boolean;
15358
15343
  /**
15359
15344
  * Image Size
15360
- * @description The size of the generated image.
15345
+ * @description The size of the generated image. Use 'auto' to match the input image size (or 1024x1024 if no image).
15361
15346
  * @default square_hd
15362
15347
  */
15363
15348
  image_size?:
@@ -15369,13 +15354,24 @@ export interface ZImageTurboTilingLoraInput {
15369
15354
  | 'portrait_16_9'
15370
15355
  | 'landscape_4_3'
15371
15356
  | 'landscape_16_9'
15357
+ | 'auto'
15372
15358
  );
15359
+ /**
15360
+ * Image URL
15361
+ * @description URL of an image for image-to-image or inpainting. When provided without mask_image_url, performs image-to-image; with mask_image_url, performs inpainting.
15362
+ */
15363
+ image_url?: string;
15373
15364
  /**
15374
15365
  * Loras
15375
15366
  * @description List of LoRA weights to apply (maximum 3).
15376
15367
  * @default []
15377
15368
  */
15378
15369
  loras?: Components.LoRAInput_2[];
15370
+ /**
15371
+ * Mask Image URL
15372
+ * @description URL of a mask image for inpainting. White regions are regenerated, black regions are preserved. Requires image_url.
15373
+ */
15374
+ mask_image_url?: string;
15379
15375
  /**
15380
15376
  * Number of Images
15381
15377
  * @description The number of images to generate.
@@ -15407,6 +15403,12 @@ export interface ZImageTurboTilingLoraInput {
15407
15403
  * will output the same image every time.
15408
15404
  */
15409
15405
  seed?: number;
15406
+ /**
15407
+ * Strength
15408
+ * @description How much to transform the input image. Only used when image_url is provided.
15409
+ * @default 0.6
15410
+ */
15411
+ strength?: number;
15410
15412
  /**
15411
15413
  * Sync Mode
15412
15414
  * @description If `True`, the media will be returned as a data URI and the output data won't be available in the request history.
@@ -15458,7 +15460,7 @@ export interface ZImageTurboTilingInput {
15458
15460
  enable_safety_checker?: boolean;
15459
15461
  /**
15460
15462
  * Image Size
15461
- * @description The size of the generated image.
15463
+ * @description The size of the generated image. Use 'auto' to match the input image size (or 1024x1024 if no image).
15462
15464
  * @default square_hd
15463
15465
  */
15464
15466
  image_size?:
@@ -15470,108 +15472,125 @@ export interface ZImageTurboTilingInput {
15470
15472
  | 'portrait_16_9'
15471
15473
  | 'landscape_4_3'
15472
15474
  | 'landscape_16_9'
15475
+ | 'auto'
15473
15476
  );
15474
15477
  /**
15475
- * Number of Images
15476
- * @description The number of images to generate.
15477
- * @default 1
15478
- */
15479
- num_images?: number;
15480
- /**
15481
- * Number of Inference Steps
15482
- * @description The number of inference steps to perform.
15483
- * @default 8
15484
- */
15485
- num_inference_steps?: number;
15486
- /**
15487
- * Output Format
15488
- * @description The format of the generated image.
15489
- * @default png
15490
- * @enum {string}
15491
- */
15492
- output_format?: 'jpeg' | 'png' | 'webp';
15493
- /**
15494
- * Prompt
15495
- * @description The prompt to generate an image from.
15496
- * @example A hyper-realistic, high-resolution 4k texture of an ancient weathered brick wall heavily overgrown with lush green moss and soft lichens. The bricks are aged, featuring deep earthy tones, natural cracks, and gritty textures. Vibrant emerald moss fills the mortar lines and spills over the rough surfaces of the stones. Uniform, flat cinematic lighting ensures no harsh shadows, highlighting the intricate organic details and damp stone surfaces. The composition is a perfectly balanced overhead view, showcasing a rich tapestry of botanical growth and masonry craftsmanship with professional clarity and hyper-detailed grit.
15497
- */
15498
- prompt: string;
15499
- /**
15500
- * Seed
15501
- * @description The same seed and the same prompt given to the same version of the model
15502
- * will output the same image every time.
15503
- */
15504
- seed?: number;
15505
- /**
15506
- * Sync Mode
15507
- * @description If `True`, the media will be returned as a data URI and the output data won't be available in the request history.
15508
- * @default false
15509
- */
15510
- sync_mode?: boolean;
15511
- /**
15512
- * Tile Size
15513
- * @description Tile size in latent space (64 = 512px, 128 = 1024px, 256 = 2048px).
15514
- * @default 128
15515
- */
15516
- tile_size?: number;
15517
- /**
15518
- * Tile Stride
15519
- * @description Tile stride in latent space. (32 = 256px, 64 = 512px, 128 = 1024px).
15520
- * @default 64
15521
- */
15522
- tile_stride?: number;
15523
- /**
15524
- * Tiling Mode
15525
- * @description Tiling direction: 'both' (omnidirectional), 'horizontal' (left-right only), 'vertical' (top-bottom only).
15526
- * @default both
15527
- * @enum {string}
15528
- */
15529
- tiling_mode?: 'both' | 'horizontal' | 'vertical';
15530
- }
15531
-
15532
- export interface ZImageTurboTilingOutput extends SharedType_390 {}
15533
-
15534
- export interface ZImageTurboLoraInput {
15535
- /**
15536
- * Acceleration
15537
- * @description The acceleration level to use.
15538
- * @default regular
15539
- * @enum {string}
15540
- */
15541
- acceleration?: 'none' | 'regular' | 'high';
15542
- /**
15543
- * Enable Prompt Expansion
15544
- * @description Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.
15545
- * @default false
15546
- */
15547
- enable_prompt_expansion?: boolean;
15548
- /**
15549
- * Enable Safety Checker
15550
- * @description If set to true, the safety checker will be enabled.
15551
- * @default true
15552
- */
15553
- enable_safety_checker?: boolean;
15554
- /**
15555
- * Image Size
15556
- * @description The size of the generated image.
15557
- * @default landscape_4_3
15478
+ * Image URL
15479
+ * @description URL of an image for image-to-image or inpainting. When provided without mask_image_url, performs image-to-image; with mask_image_url, performs inpainting.
15558
15480
  */
15559
- image_size?:
15560
- | Components.ImageSize
15561
- | (
15562
- | 'square_hd'
15563
- | 'square'
15564
- | 'portrait_4_3'
15565
- | 'portrait_16_9'
15566
- | 'landscape_4_3'
15567
- | 'landscape_16_9'
15568
- );
15481
+ image_url?: string;
15569
15482
  /**
15570
- * Loras
15571
- * @description List of LoRA weights to apply (maximum 3).
15572
- * @default []
15483
+ * Mask Image URL
15484
+ * @description URL of a mask image for inpainting. White regions are regenerated, black regions are preserved. Requires image_url.
15573
15485
  */
15574
- loras?: Components.LoRAInput_2[];
15486
+ mask_image_url?: string;
15487
+ /**
15488
+ * Number of Images
15489
+ * @description The number of images to generate.
15490
+ * @default 1
15491
+ */
15492
+ num_images?: number;
15493
+ /**
15494
+ * Number of Inference Steps
15495
+ * @description The number of inference steps to perform.
15496
+ * @default 8
15497
+ */
15498
+ num_inference_steps?: number;
15499
+ /**
15500
+ * Output Format
15501
+ * @description The format of the generated image.
15502
+ * @default png
15503
+ * @enum {string}
15504
+ */
15505
+ output_format?: 'jpeg' | 'png' | 'webp';
15506
+ /**
15507
+ * Prompt
15508
+ * @description The prompt to generate an image from.
15509
+ * @example A hyper-realistic, high-resolution 4k texture of an ancient weathered brick wall heavily overgrown with lush green moss and soft lichens. The bricks are aged, featuring deep earthy tones, natural cracks, and gritty textures. Vibrant emerald moss fills the mortar lines and spills over the rough surfaces of the stones. Uniform, flat cinematic lighting ensures no harsh shadows, highlighting the intricate organic details and damp stone surfaces. The composition is a perfectly balanced overhead view, showcasing a rich tapestry of botanical growth and masonry craftsmanship with professional clarity and hyper-detailed grit.
15510
+ */
15511
+ prompt: string;
15512
+ /**
15513
+ * Seed
15514
+ * @description The same seed and the same prompt given to the same version of the model
15515
+ * will output the same image every time.
15516
+ */
15517
+ seed?: number;
15518
+ /**
15519
+ * Strength
15520
+ * @description How much to transform the input image. Only used when image_url is provided.
15521
+ * @default 0.6
15522
+ */
15523
+ strength?: number;
15524
+ /**
15525
+ * Sync Mode
15526
+ * @description If `True`, the media will be returned as a data URI and the output data won't be available in the request history.
15527
+ * @default false
15528
+ */
15529
+ sync_mode?: boolean;
15530
+ /**
15531
+ * Tile Size
15532
+ * @description Tile size in latent space (64 = 512px, 128 = 1024px, 256 = 2048px).
15533
+ * @default 128
15534
+ */
15535
+ tile_size?: number;
15536
+ /**
15537
+ * Tile Stride
15538
+ * @description Tile stride in latent space. (32 = 256px, 64 = 512px, 128 = 1024px).
15539
+ * @default 64
15540
+ */
15541
+ tile_stride?: number;
15542
+ /**
15543
+ * Tiling Mode
15544
+ * @description Tiling direction: 'both' (omnidirectional), 'horizontal' (left-right only), 'vertical' (top-bottom only).
15545
+ * @default both
15546
+ * @enum {string}
15547
+ */
15548
+ tiling_mode?: 'both' | 'horizontal' | 'vertical';
15549
+ }
15550
+
15551
+ export interface ZImageTurboTilingOutput extends SharedType_390 {}
15552
+
15553
+ export interface ZImageTurboLoraInput {
15554
+ /**
15555
+ * Acceleration
15556
+ * @description The acceleration level to use.
15557
+ * @default regular
15558
+ * @enum {string}
15559
+ */
15560
+ acceleration?: 'none' | 'regular' | 'high';
15561
+ /**
15562
+ * Enable Prompt Expansion
15563
+ * @description Whether to enable prompt expansion. Note: this will increase the price by 0.0025 credits per request.
15564
+ * @default false
15565
+ */
15566
+ enable_prompt_expansion?: boolean;
15567
+ /**
15568
+ * Enable Safety Checker
15569
+ * @description If set to true, the safety checker will be enabled.
15570
+ * @default true
15571
+ */
15572
+ enable_safety_checker?: boolean;
15573
+ /**
15574
+ * Image Size
15575
+ * @description The size of the generated image.
15576
+ * @default landscape_4_3
15577
+ */
15578
+ image_size?:
15579
+ | Components.ImageSize
15580
+ | (
15581
+ | 'square_hd'
15582
+ | 'square'
15583
+ | 'portrait_4_3'
15584
+ | 'portrait_16_9'
15585
+ | 'landscape_4_3'
15586
+ | 'landscape_16_9'
15587
+ );
15588
+ /**
15589
+ * Loras
15590
+ * @description List of LoRA weights to apply (maximum 3).
15591
+ * @default []
15592
+ */
15593
+ loras?: Components.LoRAInput_2[];
15575
15594
  /**
15576
15595
  * Number of Images
15577
15596
  * @description The number of images to generate.
@@ -17702,13 +17721,6 @@ export interface WhisperInput {
17702
17721
  * @enum {string}
17703
17722
  */
17704
17723
  task?: 'transcribe' | 'translate';
17705
- /**
17706
- * Version
17707
- * @description Version of the model to use. All of the models are the Whisper large variant.
17708
- * @default 3
17709
- * @constant
17710
- */
17711
- version?: '3';
17712
17724
  }
17713
17725
 
17714
17726
  export interface WhisperOutput {
@@ -17830,6 +17842,7 @@ export interface WhisperOutput {
17830
17842
  /**
17831
17843
  * Text
17832
17844
  * @description Transcription of the audio file
17845
+ * @example María, ¿qué cenamos hoy? No sé, ¿qué cenamos? ¿Cenamos pollo frito o pollo asado o algo? Mejor a la plancha, quiero una salada. A la plancha, vale. Y hacemos una ensalada con tomate y esas cosas. Vale. Pues eso lo hacemos, ¿vale? Venga, vale.
17833
17846
  */
17834
17847
  text: string;
17835
17848
  }
@@ -25130,7 +25143,7 @@ export interface Swin2srInput {
25130
25143
  task?: 'classical_sr' | 'compressed_sr' | 'real_sr';
25131
25144
  }
25132
25145
 
25133
- export interface Swin2srOutput extends SharedType_e43 {}
25146
+ export interface Swin2srOutput extends SharedType_357 {}
25134
25147
 
25135
25148
  export interface StepxEdit2Input {
25136
25149
  /**
@@ -25483,7 +25496,6 @@ export interface SteadyDancerOutput {
25483
25496
  */
25484
25497
  seed: number;
25485
25498
  /**
25486
- * Video
25487
25499
  * @description The generated dance animation video.
25488
25500
  * @example {
25489
25501
  * "file_size": 7772111,
@@ -25492,7 +25504,7 @@ export interface SteadyDancerOutput {
25492
25504
  * "url": "https://v3b.fal.media/files/b/0a87871b/ll5ps0ZyBgxBkuWz-fHcT_output_with_audio.mp4"
25493
25505
  * }
25494
25506
  */
25495
- video: Components.File_1;
25507
+ video: Components.File;
25496
25508
  }
25497
25509
 
25498
25510
  export interface StarVectorInput {
@@ -26009,6 +26021,7 @@ export interface StableDiffusionV15Input {
26009
26021
  * Seed
26010
26022
  * @description The same seed and the same prompt given to the same version of Stable Diffusion
26011
26023
  * will output the same image every time.
26024
+ * @default null
26012
26025
  */
26013
26026
  seed?: number;
26014
26027
  /**
@@ -27990,54 +28003,67 @@ export interface SanaSprintOutput extends SharedType_7c6 {}
27990
28003
 
27991
28004
  export interface SanaVideoInput {
27992
28005
  /**
27993
- * Fps
27994
- * @description Frames per second for the output video
28006
+ * Aspect Ratio
28007
+ * @description The aspect ratio of the output video. Only used when resolution is '720p'.
28008
+ * @default 16:9
28009
+ * @enum {string}
28010
+ */
28011
+ aspect_ratio?: '16:9' | '9:16' | '4:3' | '3:4' | '1:1';
28012
+ /**
28013
+ * Enable Safety Checker
28014
+ * @description Enable safety checking of the generated video.
28015
+ * @default true
28016
+ */
28017
+ enable_safety_checker?: boolean;
28018
+ /**
28019
+ * Frames Per Second
28020
+ * @description Frames per second for the output video.
27995
28021
  * @default 16
27996
28022
  */
27997
- fps?: number;
28023
+ frames_per_second?: number;
27998
28024
  /**
27999
28025
  * Guidance Scale
28000
- * @description Guidance scale for generation (higher = more prompt adherence)
28026
+ * @description Guidance scale for generation (higher = more prompt adherence).
28001
28027
  * @default 6
28002
28028
  */
28003
28029
  guidance_scale?: number;
28004
28030
  /**
28005
28031
  * Motion Score
28006
- * @description Motion intensity score (higher = more motion)
28032
+ * @description Motion intensity score (higher = more motion).
28007
28033
  * @default 30
28008
28034
  */
28009
28035
  motion_score?: number;
28010
28036
  /**
28011
28037
  * Negative Prompt
28012
- * @description The negative prompt describing what to avoid in the generation
28038
+ * @description The negative prompt describing what to avoid in the generation.
28013
28039
  * @default A chaotic sequence with misshapen, deformed limbs in heavy motion blur, sudden disappearance, jump cuts, jerky movements, rapid shot changes, frames out of sync, inconsistent character shapes, temporal artifacts, jitter, and ghosting effects, creating a disorienting visual experience.
28014
28040
  */
28015
28041
  negative_prompt?: string;
28016
28042
  /**
28017
28043
  * Num Frames
28018
- * @description Number of frames to generate
28044
+ * @description Number of frames to generate.
28019
28045
  * @default 81
28020
28046
  */
28021
28047
  num_frames?: number;
28022
28048
  /**
28023
28049
  * Num Inference Steps
28024
- * @description Number of denoising steps
28050
+ * @description Number of denoising steps.
28025
28051
  * @default 28
28026
28052
  */
28027
28053
  num_inference_steps?: number;
28028
28054
  /**
28029
28055
  * Prompt
28030
- * @description The text prompt describing the video to generate
28056
+ * @description The text prompt describing the video to generate.
28031
28057
  * @example Evening, backlight, side lighting, soft light, high contrast, mid-shot, centered composition, clean solo shot, warm color. A young Caucasian man stands in a forest, golden light glimmers on his hair as sunlight filters through the leaves.
28032
28058
  */
28033
28059
  prompt: string;
28034
28060
  /**
28035
28061
  * Resolution
28036
- * @description The resolution of the output video
28062
+ * @description The resolution of the output video.
28037
28063
  * @default 480p
28038
28064
  * @enum {string}
28039
28065
  */
28040
- resolution?: '480p';
28066
+ resolution?: '480p' | '720p';
28041
28067
  /**
28042
28068
  * Seed
28043
28069
  * @description Random seed for reproducible generation. If not provided, a random seed will be used.
@@ -28048,18 +28074,24 @@ export interface SanaVideoInput {
28048
28074
  export interface SanaVideoOutput {
28049
28075
  /**
28050
28076
  * Seed
28051
- * @description The random seed used for the generation process
28077
+ * @description The random seed used for the generation process.
28052
28078
  */
28053
28079
  seed: number;
28054
28080
  /**
28055
- * Video
28056
- * @description Generated video file
28081
+ * Timings
28082
+ * @description Performance timing breakdown.
28083
+ */
28084
+ timings: {
28085
+ [key: string]: number;
28086
+ };
28087
+ /**
28088
+ * @description Generated video file.
28057
28089
  * @example {
28058
28090
  * "content_type": "video/mp4",
28059
28091
  * "url": "https://v3b.fal.media/files/b/zebra/TipA9XXsXRYlB6vK6PQ0l_output.mp4"
28060
28092
  * }
28061
28093
  */
28062
- video: Components.File_1;
28094
+ video: Components.File;
28063
28095
  }
28064
28096
 
28065
28097
  export interface SanaInput extends SharedType_5f3 {}
@@ -28106,15 +28138,15 @@ export interface Sam2VideoInput {
28106
28138
  * @example [
28107
28139
  * {
28108
28140
  * "y": 350,
28109
- * "x": 210,
28141
+ * "label": 1,
28110
28142
  * "frame_index": 0,
28111
- * "label": 1
28143
+ * "x": 210
28112
28144
  * },
28113
28145
  * {
28114
28146
  * "y": 220,
28115
- * "x": 250,
28147
+ * "label": 1,
28116
28148
  * "frame_index": 0,
28117
- * "label": 1
28149
+ * "x": 250
28118
28150
  * }
28119
28151
  * ]
28120
28152
  */
@@ -28173,8 +28205,8 @@ export interface Sam2ImageInput {
28173
28205
  * @example [
28174
28206
  * {
28175
28207
  * "y": 375,
28176
- * "x": 500,
28177
- * "label": 1
28208
+ * "label": 1,
28209
+ * "x": 500
28178
28210
  * }
28179
28211
  * ]
28180
28212
  */
@@ -28614,6 +28646,13 @@ export interface Sam3VideoInput {
28614
28646
  * @description [DEPRECATED] Use 'prompt' instead. Kept for backward compatibility.
28615
28647
  */
28616
28648
  text_prompt?: string;
28649
+ /**
28650
+ * Video Output Type
28651
+ * @description The output type of the generated video.
28652
+ * @default X264 (.mp4)
28653
+ * @enum {string}
28654
+ */
28655
+ video_output_type?: 'X264 (.mp4)' | 'VP9 (.webm)';
28617
28656
  /**
28618
28657
  * Video Url
28619
28658
  * @description The URL of the video to be segmented.
@@ -28971,7 +29010,7 @@ export interface Sa2va8bVideoOutput extends SharedType_800 {}
28971
29010
 
28972
29011
  export interface Sa2va8bImageInput extends SharedType_f51 {}
28973
29012
 
28974
- export interface Sa2va8bImageOutput extends SharedType_100 {}
29013
+ export interface Sa2va8bImageOutput extends SharedType_fda {}
28975
29014
 
28976
29015
  export interface Sa2va4bVideoInput extends SharedType_5f5 {}
28977
29016
 
@@ -28979,7 +29018,7 @@ export interface Sa2va4bVideoOutput extends SharedType_800 {}
28979
29018
 
28980
29019
  export interface Sa2va4bImageInput extends SharedType_f51 {}
28981
29020
 
28982
- export interface Sa2va4bImageOutput extends SharedType_100 {}
29021
+ export interface Sa2va4bImageOutput extends SharedType_fda {}
28983
29022
 
28984
29023
  export interface RifeVideoInput {
28985
29024
  /**
@@ -36099,6 +36138,98 @@ export interface PhotomakerOutput {
36099
36138
  seed: number;
36100
36139
  }
36101
36140
 
36141
+ export interface PersonaplexRealtimeInput {
36142
+ /**
36143
+ * Audio
36144
+ * Format: binary
36145
+ * @description Input audio chunk (PCM s16le, 24kHz mono). Base64-encoded in JSON transport.
36146
+ */
36147
+ audio: string;
36148
+ /**
36149
+ * Prompt
36150
+ * @description Text prompt describing the AI persona and conversation context.
36151
+ * @default You are a wise and friendly teacher. Answer questions or provide advice in a clear and engaging way.
36152
+ * @example You work for SwiftPlex Appliances which is a appliance repair company and your name is Farhod Toshmatov. Information: The dishwasher model is out of stock for replacement parts; we can use an alternative part with a 3-day delay. Labor cost remains $60 per hour.
36153
+ */
36154
+ prompt?: string;
36155
+ /**
36156
+ * Seed
36157
+ * @description Random seed for reproducibility.
36158
+ * @default null
36159
+ */
36160
+ seed?: number;
36161
+ /**
36162
+ * Temperature Audio
36163
+ * @description Audio sampling temperature. Higher values produce more diverse outputs.
36164
+ * @default 0.8
36165
+ */
36166
+ temperature_audio?: number;
36167
+ /**
36168
+ * Temperature Text
36169
+ * @description Text sampling temperature. Higher values produce more diverse outputs.
36170
+ * @default 0.7
36171
+ */
36172
+ temperature_text?: number;
36173
+ /**
36174
+ * Top K Audio
36175
+ * @description Top-K sampling for audio tokens.
36176
+ * @default 250
36177
+ */
36178
+ top_k_audio?: number;
36179
+ /**
36180
+ * Top K Text
36181
+ * @description Top-K sampling for text tokens.
36182
+ * @default 25
36183
+ */
36184
+ top_k_text?: number;
36185
+ /**
36186
+ * Voice
36187
+ * @description Voice ID for the AI response. NAT = natural, VAR = variety. F = female, M = male. Ignored when voice_audio_url is provided.
36188
+ * @default NATF2
36189
+ * @enum {string}
36190
+ */
36191
+ voice?:
36192
+ | 'NATF0'
36193
+ | 'NATF1'
36194
+ | 'NATF2'
36195
+ | 'NATF3'
36196
+ | 'NATM0'
36197
+ | 'NATM1'
36198
+ | 'NATM2'
36199
+ | 'NATM3'
36200
+ | 'VARF0'
36201
+ | 'VARF1'
36202
+ | 'VARF2'
36203
+ | 'VARF3'
36204
+ | 'VARF4'
36205
+ | 'VARM0'
36206
+ | 'VARM1'
36207
+ | 'VARM2'
36208
+ | 'VARM3'
36209
+ | 'VARM4';
36210
+ /**
36211
+ * Voice Audio Url
36212
+ * @description URL to a voice sample audio for on-the-fly voice cloning. When provided, the AI responds in the cloned voice instead of the preset 'voice'. 10+ seconds of clear speech recommended. Billed at 2x rate.
36213
+ * @default null
36214
+ */
36215
+ voice_audio_url?: string;
36216
+ }
36217
+
36218
+ export interface PersonaplexRealtimeOutput {
36219
+ /**
36220
+ * Audio
36221
+ * Format: binary
36222
+ * @description Generated audio chunk (PCM s16le, 24kHz mono). Base64-encoded in JSON transport.
36223
+ */
36224
+ audio: string;
36225
+ /**
36226
+ * Text
36227
+ * @description Generated text tokens for this chunk.
36228
+ * @default
36229
+ */
36230
+ text?: string;
36231
+ }
36232
+
36102
36233
  export interface PersonaplexInput {
36103
36234
  /**
36104
36235
  * Audio Url
@@ -38156,7 +38287,6 @@ export interface MmaudioV2TextToAudioInput {
38156
38287
 
38157
38288
  export interface MmaudioV2TextToAudioOutput {
38158
38289
  /**
38159
- * Audio
38160
38290
  * @description The generated audio.
38161
38291
  * @example {
38162
38292
  * "file_size": 1001342,
@@ -38165,7 +38295,7 @@ export interface MmaudioV2TextToAudioOutput {
38165
38295
  * "url": "https://storage.googleapis.com/falserverless/model_tests/video_models/mmaudio_output.flac"
38166
38296
  * }
38167
38297
  */
38168
- audio: Components.File_1;
38298
+ audio: Components.File;
38169
38299
  }
38170
38300
 
38171
38301
  export interface MmaudioV2Input {
@@ -38220,7 +38350,6 @@ export interface MmaudioV2Input {
38220
38350
 
38221
38351
  export interface MmaudioV2Output {
38222
38352
  /**
38223
- * Video
38224
38353
  * @description The generated video with the lip sync.
38225
38354
  * @example {
38226
38355
  * "file_size": 1001342,
@@ -38229,7 +38358,7 @@ export interface MmaudioV2Output {
38229
38358
  * "url": "https://storage.googleapis.com/falserverless/model_tests/video_models/mmaudio_output.mp4"
38230
38359
  * }
38231
38360
  */
38232
- video: Components.File_1;
38361
+ video: Components.File;
38233
38362
  }
38234
38363
 
38235
38364
  export interface MixDehazeNetInput {
@@ -38252,7 +38381,13 @@ export interface MixDehazeNetInput {
38252
38381
  seed?: number;
38253
38382
  }
38254
38383
 
38255
- export interface MixDehazeNetOutput extends SharedType_e43 {}
38384
+ export interface MixDehazeNetOutput {
38385
+ /**
38386
+ * Image
38387
+ * @description The generated image file info.
38388
+ */
38389
+ image: Components.Image_2;
38390
+ }
38256
38391
 
38257
38392
  export interface MinimaxVoiceDesignInput {
38258
38393
  /**
@@ -40787,6 +40922,12 @@ export interface Ltx2VideoTrainerInput {
40787
40922
  * @example false
40788
40923
  */
40789
40924
  auto_scale_input?: boolean;
40925
+ /**
40926
+ * Debug Dataset
40927
+ * @description When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.
40928
+ * @default false
40929
+ */
40930
+ debug_dataset?: boolean;
40790
40931
  /**
40791
40932
  * First Frame Conditioning P
40792
40933
  * @description Probability of conditioning on the first frame during training. Higher values improve image-to-video performance.
@@ -40931,159 +41072,13 @@ export interface Ltx2VideoTrainerInput {
40931
41072
  with_audio?: boolean;
40932
41073
  }
40933
41074
 
40934
- export interface Ltx2VideoTrainerOutput extends SharedType_f7a {}
40935
-
40936
- export interface Ltx2V2vTrainerInput {
40937
- /**
40938
- * Aspect Ratio
40939
- * @description Aspect ratio to use for training.
40940
- * @default 1:1
40941
- * @example 1:1
40942
- * @enum {string}
40943
- */
40944
- aspect_ratio?: '16:9' | '1:1' | '9:16';
40945
- /**
40946
- * Auto Scale Input
40947
- * @description If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.
40948
- * @default false
40949
- * @example false
40950
- */
40951
- auto_scale_input?: boolean;
40952
- /**
40953
- * First Frame Conditioning P
40954
- * @description Probability of conditioning on the first frame during training. Lower values work better for video-to-video transformation.
40955
- * @default 0.1
40956
- */
40957
- first_frame_conditioning_p?: number;
40958
- /**
40959
- * Frame Rate
40960
- * @description Target frames per second for the video.
40961
- * @default 25
40962
- * @example 25
40963
- */
40964
- frame_rate?: number;
40965
- /**
40966
- * Learning Rate
40967
- * @description Learning rate for optimization. Higher values can lead to faster training but may cause overfitting.
40968
- * @default 0.0002
40969
- * @example 0.0002
40970
- */
40971
- learning_rate?: number;
40972
- /**
40973
- * Number Of Frames
40974
- * @description Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97).
40975
- * @default 89
40976
- * @example 89
40977
- */
40978
- number_of_frames?: number;
40979
- /**
40980
- * Number Of Steps
40981
- * @description The number of training steps.
40982
- * @default 2000
40983
- * @example 2000
40984
- */
40985
- number_of_steps?: number;
40986
- /**
40987
- * Rank
40988
- * @description The rank of the LoRA adaptation. Higher values increase capacity but use more memory.
40989
- * @default 32
40990
- * @example 32
40991
- * @enum {integer}
40992
- */
40993
- rank?: 8 | 16 | 32 | 64 | 128;
40994
- /**
40995
- * Resolution
40996
- * @description Resolution to use for training. Higher resolutions require more memory.
40997
- * @default medium
40998
- * @example medium
40999
- * @enum {string}
41000
- */
41001
- resolution?: 'low' | 'medium' | 'high';
41002
- /**
41003
- * Split Input Duration Threshold
41004
- * @description The duration threshold in seconds. If a video is longer than this, it will be split into scenes.
41005
- * @default 30
41006
- * @example 30
41007
- */
41008
- split_input_duration_threshold?: number;
41009
- /**
41010
- * Split Input Into Scenes
41011
- * @description If true, videos above a certain duration threshold will be split into scenes.
41012
- * @default true
41013
- * @example true
41014
- */
41015
- split_input_into_scenes?: boolean;
41016
- /**
41017
- * Stg Scale
41018
- * @description STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.
41019
- * @default 1
41020
- */
41021
- stg_scale?: number;
41022
- /**
41023
- * Training Data Url
41024
- * @description URL to zip archive with videos or images. Try to use at least 10 files, although more is better.
41025
- *
41026
- * **Supported video formats:** .mp4, .mov, .avi, .mkv
41027
- * **Supported image formats:** .png, .jpg, .jpeg
41028
- *
41029
- * Note: The dataset must contain ONLY videos OR ONLY images - mixed datasets are not supported.
41030
- *
41031
- * The archive can also contain text files with captions. Each text file should have the same name as the media file it corresponds to.
41032
- */
41033
- training_data_url: string;
41034
- /**
41035
- * Trigger Phrase
41036
- * @description A phrase that will trigger the LoRA style. Will be prepended to captions during training.
41037
- * @default
41038
- * @example
41039
- */
41040
- trigger_phrase?: string;
41041
- /**
41042
- * Validation
41043
- * @description A list of validation inputs with prompts and reference videos.
41044
- * @default []
41045
- */
41046
- validation?: Components.V2VValidation[];
41047
- /**
41048
- * Validation Aspect Ratio
41049
- * @description The aspect ratio to use for validation.
41050
- * @default 1:1
41051
- * @example 1:1
41052
- * @enum {string}
41053
- */
41054
- validation_aspect_ratio?: '16:9' | '1:1' | '9:16';
41055
- /**
41056
- * Validation Frame Rate
41057
- * @description Target frames per second for validation videos.
41058
- * @default 25
41059
- * @example 25
41060
- */
41061
- validation_frame_rate?: number;
41062
- /**
41063
- * Validation Negative Prompt
41064
- * @description A negative prompt to use for validation.
41065
- * @default worst quality, inconsistent motion, blurry, jittery, distorted
41066
- */
41067
- validation_negative_prompt?: string;
41068
- /**
41069
- * Validation Number Of Frames
41070
- * @description The number of frames in validation videos.
41071
- * @default 89
41072
- * @example 89
41073
- */
41074
- validation_number_of_frames?: number;
41075
- /**
41076
- * Validation Resolution
41077
- * @description The resolution to use for validation.
41078
- * @default high
41079
- * @example high
41080
- * @enum {string}
41081
- */
41082
- validation_resolution?: 'low' | 'medium' | 'high';
41075
+ export interface Ltx2VideoTrainerOutput {
41076
+ config_file: Components.File;
41077
+ debug_dataset?: Components.File;
41078
+ lora_file: Components.File;
41079
+ video?: Components.File;
41083
41080
  }
41084
41081
 
41085
- export interface Ltx2V2vTrainerOutput extends SharedType_f7a {}
41086
-
41087
41082
  export interface LtxVideoImageToVideoInput {
41088
41083
  /**
41089
41084
  * Guidance Scale
@@ -41490,6 +41485,13 @@ export interface LtxVideoLoraMulticonditioningInput {
41490
41485
  * @enum {string}
41491
41486
  */
41492
41487
  aspect_ratio?: '16:9' | '1:1' | '9:16' | 'auto';
41488
+ /**
41489
+ * Enable Prompt Expansion
41490
+ * @description Whether to expand the prompt using the LLM.
41491
+ * @default false
41492
+ * @example false
41493
+ */
41494
+ enable_prompt_expansion?: boolean;
41493
41495
  /**
41494
41496
  * Enable Safety Checker
41495
41497
  * @description Whether to enable the safety checker.
@@ -41498,19 +41500,12 @@ export interface LtxVideoLoraMulticonditioningInput {
41498
41500
  */
41499
41501
  enable_safety_checker?: boolean;
41500
41502
  /**
41501
- * Expand Prompt
41502
- * @description Whether to expand the prompt using the LLM.
41503
- * @default false
41504
- * @example false
41505
- */
41506
- expand_prompt?: boolean;
41507
- /**
41508
- * Frame Rate
41503
+ * Frames Per Second
41509
41504
  * @description The frame rate of the video.
41510
41505
  * @default 25
41511
41506
  * @example 25
41512
41507
  */
41513
- frame_rate?: number;
41508
+ frames_per_second?: number;
41514
41509
  /**
41515
41510
  * Images
41516
41511
  * @description The image conditions to use for generation.
@@ -41541,6 +41536,13 @@ export interface LtxVideoLoraMulticonditioningInput {
41541
41536
  * @default blurry, low quality, low resolution, inconsistent motion, jittery, distorted
41542
41537
  */
41543
41538
  negative_prompt?: string;
41539
+ /**
41540
+ * Num Inference Steps
41541
+ * @description The number of inference steps to use.
41542
+ * @default 30
41543
+ * @example 30
41544
+ */
41545
+ num_inference_steps?: number;
41544
41546
  /**
41545
41547
  * Number Of Frames
41546
41548
  * @description The number of frames in the video.
@@ -41548,13 +41550,6 @@ export interface LtxVideoLoraMulticonditioningInput {
41548
41550
  * @example 89
41549
41551
  */
41550
41552
  number_of_frames?: number;
41551
- /**
41552
- * Number Of Steps
41553
- * @description The number of inference steps to use.
41554
- * @default 30
41555
- * @example 30
41556
- */
41557
- number_of_steps?: number;
41558
41553
  /**
41559
41554
  * Prompt
41560
41555
  * @description The prompt to generate the video from.
@@ -41619,6 +41614,13 @@ export interface LtxVideoLoraImageToVideoInput {
41619
41614
  * @enum {string}
41620
41615
  */
41621
41616
  aspect_ratio?: '16:9' | '1:1' | '9:16' | 'auto';
41617
+ /**
41618
+ * Enable Prompt Expansion
41619
+ * @description Whether to expand the prompt using the LLM.
41620
+ * @default false
41621
+ * @example false
41622
+ */
41623
+ enable_prompt_expansion?: boolean;
41622
41624
  /**
41623
41625
  * Enable Safety Checker
41624
41626
  * @description Whether to enable the safety checker.
@@ -41627,19 +41629,12 @@ export interface LtxVideoLoraImageToVideoInput {
41627
41629
  */
41628
41630
  enable_safety_checker?: boolean;
41629
41631
  /**
41630
- * Expand Prompt
41631
- * @description Whether to expand the prompt using the LLM.
41632
- * @default false
41633
- * @example false
41634
- */
41635
- expand_prompt?: boolean;
41636
- /**
41637
- * Frame Rate
41632
+ * Frames Per Second
41638
41633
  * @description The frame rate of the video.
41639
41634
  * @default 25
41640
41635
  * @example 25
41641
41636
  */
41642
- frame_rate?: number;
41637
+ frames_per_second?: number;
41643
41638
  /**
41644
41639
  * Image Url
41645
41640
  * @description The URL of the image to use as input.
@@ -41658,6 +41653,13 @@ export interface LtxVideoLoraImageToVideoInput {
41658
41653
  * @default blurry, low quality, low resolution, inconsistent motion, jittery, distorted
41659
41654
  */
41660
41655
  negative_prompt?: string;
41656
+ /**
41657
+ * Num Inference Steps
41658
+ * @description The number of inference steps to use.
41659
+ * @default 30
41660
+ * @example 30
41661
+ */
41662
+ num_inference_steps?: number;
41661
41663
  /**
41662
41664
  * Number Of Frames
41663
41665
  * @description The number of frames in the video.
@@ -41665,13 +41667,6 @@ export interface LtxVideoLoraImageToVideoInput {
41665
41667
  * @example 89
41666
41668
  */
41667
41669
  number_of_frames?: number;
41668
- /**
41669
- * Number Of Steps
41670
- * @description The number of inference steps to use.
41671
- * @default 30
41672
- * @example 30
41673
- */
41674
- number_of_steps?: number;
41675
41670
  /**
41676
41671
  * Prompt
41677
41672
  * @description The prompt to generate the video from.
@@ -42148,8 +42143,8 @@ export interface LtxVideo13bDevExtendInput {
42148
42143
  * @description Video to be extended.
42149
42144
  * @example {
42150
42145
  * "video_url": "https://storage.googleapis.com/falserverless/web-examples/wan/t2v.mp4",
42151
- * "start_frame_num": 0,
42152
42146
  * "reverse_video": false,
42147
+ * "start_frame_num": 0,
42153
42148
  * "limit_num_frames": false,
42154
42149
  * "resample_fps": false,
42155
42150
  * "strength": 1,
@@ -43207,7 +43202,7 @@ export interface Ltx219bVideoToVideoLoraInput {
43207
43202
  video_write_mode?: 'fast' | 'balanced' | 'small';
43208
43203
  }
43209
43204
 
43210
- export interface Ltx219bVideoToVideoLoraOutput extends SharedType_3b0 {}
43205
+ export interface Ltx219bVideoToVideoLoraOutput extends SharedType_1f5 {}
43211
43206
 
43212
43207
  export interface Ltx219bVideoToVideoInput {
43213
43208
  /**
@@ -43429,7 +43424,7 @@ export interface Ltx219bVideoToVideoInput {
43429
43424
  video_write_mode?: 'fast' | 'balanced' | 'small';
43430
43425
  }
43431
43426
 
43432
- export interface Ltx219bVideoToVideoOutput extends SharedType_3b0 {}
43427
+ export interface Ltx219bVideoToVideoOutput extends SharedType_1f5 {}
43433
43428
 
43434
43429
  export interface Ltx219bTextToVideoLoraInput {
43435
43430
  /**
@@ -43576,7 +43571,7 @@ export interface Ltx219bTextToVideoLoraInput {
43576
43571
  video_write_mode?: 'fast' | 'balanced' | 'small';
43577
43572
  }
43578
43573
 
43579
- export interface Ltx219bTextToVideoLoraOutput extends SharedType_857 {}
43574
+ export interface Ltx219bTextToVideoLoraOutput extends SharedType_6ef {}
43580
43575
 
43581
43576
  export interface Ltx219bTextToVideoInput {
43582
43577
  /**
@@ -43718,7 +43713,7 @@ export interface Ltx219bTextToVideoInput {
43718
43713
  video_write_mode?: 'fast' | 'balanced' | 'small';
43719
43714
  }
43720
43715
 
43721
- export interface Ltx219bTextToVideoOutput extends SharedType_857 {}
43716
+ export interface Ltx219bTextToVideoOutput extends SharedType_6ef {}
43722
43717
 
43723
43718
  export interface Ltx219bImageToVideoLoraInput {
43724
43719
  /**
@@ -43896,7 +43891,7 @@ export interface Ltx219bImageToVideoLoraInput {
43896
43891
  video_write_mode?: 'fast' | 'balanced' | 'small';
43897
43892
  }
43898
43893
 
43899
- export interface Ltx219bImageToVideoLoraOutput extends SharedType_369 {}
43894
+ export interface Ltx219bImageToVideoLoraOutput extends SharedType_437 {}
43900
43895
 
43901
43896
  export interface Ltx219bImageToVideoInput {
43902
43897
  /**
@@ -44069,7 +44064,7 @@ export interface Ltx219bImageToVideoInput {
44069
44064
  video_write_mode?: 'fast' | 'balanced' | 'small';
44070
44065
  }
44071
44066
 
44072
- export interface Ltx219bImageToVideoOutput extends SharedType_369 {}
44067
+ export interface Ltx219bImageToVideoOutput extends SharedType_437 {}
44073
44068
 
44074
44069
  export interface Ltx219bExtendVideoLoraInput {
44075
44070
  /**
@@ -44265,7 +44260,7 @@ export interface Ltx219bExtendVideoLoraInput {
44265
44260
  video_write_mode?: 'fast' | 'balanced' | 'small';
44266
44261
  }
44267
44262
 
44268
- export interface Ltx219bExtendVideoLoraOutput extends SharedType_cb6 {}
44263
+ export interface Ltx219bExtendVideoLoraOutput extends SharedType_5db {}
44269
44264
 
44270
44265
  export interface Ltx219bExtendVideoInput {
44271
44266
  /**
@@ -44456,7 +44451,7 @@ export interface Ltx219bExtendVideoInput {
44456
44451
  video_write_mode?: 'fast' | 'balanced' | 'small';
44457
44452
  }
44458
44453
 
44459
- export interface Ltx219bExtendVideoOutput extends SharedType_cb6 {}
44454
+ export interface Ltx219bExtendVideoOutput extends SharedType_5db {}
44460
44455
 
44461
44456
  export interface Ltx219bDistilledVideoToVideoLoraInput {
44462
44457
  /**
@@ -44671,7 +44666,7 @@ export interface Ltx219bDistilledVideoToVideoLoraInput {
44671
44666
  video_write_mode?: 'fast' | 'balanced' | 'small';
44672
44667
  }
44673
44668
 
44674
- export interface Ltx219bDistilledVideoToVideoLoraOutput extends SharedType_3b0 {}
44669
+ export interface Ltx219bDistilledVideoToVideoLoraOutput extends SharedType_1f5 {}
44675
44670
 
44676
44671
  export interface Ltx219bDistilledVideoToVideoInput {
44677
44672
  /**
@@ -44881,7 +44876,7 @@ export interface Ltx219bDistilledVideoToVideoInput {
44881
44876
  video_write_mode?: 'fast' | 'balanced' | 'small';
44882
44877
  }
44883
44878
 
44884
- export interface Ltx219bDistilledVideoToVideoOutput extends SharedType_3b0 {}
44879
+ export interface Ltx219bDistilledVideoToVideoOutput extends SharedType_1f5 {}
44885
44880
 
44886
44881
  export interface Ltx219bDistilledTextToVideoLoraInput {
44887
44882
  /**
@@ -45016,7 +45011,7 @@ export interface Ltx219bDistilledTextToVideoLoraInput {
45016
45011
  video_write_mode?: 'fast' | 'balanced' | 'small';
45017
45012
  }
45018
45013
 
45019
- export interface Ltx219bDistilledTextToVideoLoraOutput extends SharedType_857 {}
45014
+ export interface Ltx219bDistilledTextToVideoLoraOutput extends SharedType_6ef {}
45020
45015
 
45021
45016
  export interface Ltx219bDistilledTextToVideoInput {
45022
45017
  /**
@@ -45146,7 +45141,7 @@ export interface Ltx219bDistilledTextToVideoInput {
45146
45141
  video_write_mode?: 'fast' | 'balanced' | 'small';
45147
45142
  }
45148
45143
 
45149
- export interface Ltx219bDistilledTextToVideoOutput extends SharedType_857 {}
45144
+ export interface Ltx219bDistilledTextToVideoOutput extends SharedType_6ef {}
45150
45145
 
45151
45146
  export interface Ltx219bDistilledImageToVideoLoraInput {
45152
45147
  /**
@@ -45312,7 +45307,7 @@ export interface Ltx219bDistilledImageToVideoLoraInput {
45312
45307
  video_write_mode?: 'fast' | 'balanced' | 'small';
45313
45308
  }
45314
45309
 
45315
- export interface Ltx219bDistilledImageToVideoLoraOutput extends SharedType_369 {}
45310
+ export interface Ltx219bDistilledImageToVideoLoraOutput extends SharedType_437 {}
45316
45311
 
45317
45312
  export interface Ltx219bDistilledImageToVideoInput {
45318
45313
  /**
@@ -45473,7 +45468,7 @@ export interface Ltx219bDistilledImageToVideoInput {
45473
45468
  video_write_mode?: 'fast' | 'balanced' | 'small';
45474
45469
  }
45475
45470
 
45476
- export interface Ltx219bDistilledImageToVideoOutput extends SharedType_369 {}
45471
+ export interface Ltx219bDistilledImageToVideoOutput extends SharedType_437 {}
45477
45472
 
45478
45473
  export interface Ltx219bDistilledExtendVideoLoraInput {
45479
45474
  /**
@@ -45657,7 +45652,7 @@ export interface Ltx219bDistilledExtendVideoLoraInput {
45657
45652
  video_write_mode?: 'fast' | 'balanced' | 'small';
45658
45653
  }
45659
45654
 
45660
- export interface Ltx219bDistilledExtendVideoLoraOutput extends SharedType_cb6 {}
45655
+ export interface Ltx219bDistilledExtendVideoLoraOutput extends SharedType_5db {}
45661
45656
 
45662
45657
  export interface Ltx219bDistilledExtendVideoInput {
45663
45658
  /**
@@ -45836,7 +45831,7 @@ export interface Ltx219bDistilledExtendVideoInput {
45836
45831
  video_write_mode?: 'fast' | 'balanced' | 'small';
45837
45832
  }
45838
45833
 
45839
- export interface Ltx219bDistilledExtendVideoOutput extends SharedType_cb6 {}
45834
+ export interface Ltx219bDistilledExtendVideoOutput extends SharedType_5db {}
45840
45835
 
45841
45836
  export interface Ltx219bDistilledAudioToVideoLoraInput {
45842
45837
  /**
@@ -49041,9 +49036,9 @@ export interface LightxRelightInput {
49041
49036
  /**
49042
49037
  * @description Relighting parameters (required for relight_condition_type='ic'). Not used for 'bg' (which expects a background image URL instead).
49043
49038
  * @example {
49044
- * "use_sky_mask": false,
49045
- * "bg_source": "Right",
49046
49039
  * "relight_prompt": "Sunlight",
49040
+ * "bg_source": "Right",
49041
+ * "use_sky_mask": false,
49047
49042
  * "cfg": 2
49048
49043
  * }
49049
49044
  */
@@ -58265,17 +58260,17 @@ export interface Hunyuan3dV3TextTo3dOutput {
58265
58260
  /**
58266
58261
  * @description URLs for different 3D model formats
58267
58262
  * @example {
58268
- * "obj": {
58269
- * "file_size": 44084728,
58270
- * "file_name": "model.obj",
58271
- * "content_type": "text/plain",
58272
- * "url": "https://v3b.fal.media/files/b/0a8686a8/AVgdsVFrGAKGAFr4e2g56_model.obj"
58273
- * },
58274
58263
  * "glb": {
58275
58264
  * "file_size": 64724836,
58276
58265
  * "file_name": "model.glb",
58277
58266
  * "content_type": "model/gltf-binary",
58278
58267
  * "url": "https://v3b.fal.media/files/b/0a8686a8/1hPquv3AqqkfnqSM9fpmB_model.glb"
58268
+ * },
58269
+ * "obj": {
58270
+ * "file_size": 44084728,
58271
+ * "file_name": "model.obj",
58272
+ * "content_type": "text/plain",
58273
+ * "url": "https://v3b.fal.media/files/b/0a8686a8/AVgdsVFrGAKGAFr4e2g56_model.obj"
58279
58274
  * }
58280
58275
  * }
58281
58276
  */
@@ -58434,17 +58429,17 @@ export interface Hunyuan3dV3ImageTo3dOutput {
58434
58429
  /**
58435
58430
  * @description URLs for different 3D model formats
58436
58431
  * @example {
58437
- * "obj": {
58438
- * "file_size": 42886419,
58439
- * "file_name": "model.obj",
58440
- * "content_type": "text/plain",
58441
- * "url": "https://v3b.fal.media/files/b/0a8686ad/ifdJskhUfQysq-NN20iQR_model.obj"
58442
- * },
58443
58432
  * "glb": {
58444
58433
  * "file_size": 64122888,
58445
58434
  * "file_name": "model.glb",
58446
58435
  * "content_type": "model/gltf-binary",
58447
58436
  * "url": "https://v3b.fal.media/files/b/0a8686ae/MQN_KtP32PbqtPr_VLcyp_model.glb"
58437
+ * },
58438
+ * "obj": {
58439
+ * "file_size": 42886419,
58440
+ * "file_name": "model.obj",
58441
+ * "content_type": "text/plain",
58442
+ * "url": "https://v3b.fal.media/files/b/0a8686ad/ifdJskhUfQysq-NN20iQR_model.obj"
58448
58443
  * }
58449
58444
  * }
58450
58445
  */
@@ -60200,8 +60195,8 @@ export interface Hunyuan_worldOutput {
60200
60195
  /**
60201
60196
  * @description The generated panorama image.
60202
60197
  * @example {
60203
- * "file_size": 2738127,
60204
60198
  * "height": 960,
60199
+ * "file_size": 2738127,
60205
60200
  * "file_name": "5db7925423b44f2a98098cd8f7cad7ec.png",
60206
60201
  * "content_type": "image/png",
60207
60202
  * "url": "https://v3.fal.media/files/kangaroo/P2AmXuLlyDIsivqjV_rAr_5db7925423b44f2a98098cd8f7cad7ec.png",
@@ -62127,8 +62122,8 @@ export interface FooocusUpscaleOrVaryInput {
62127
62122
  * Styles
62128
62123
  * @description The style to use.
62129
62124
  * @default [
62130
- * "Fooocus Sharp",
62131
62125
  * "Fooocus V2",
62126
+ * "Fooocus Sharp",
62132
62127
  * "Fooocus Enhance"
62133
62128
  * ]
62134
62129
  */
@@ -62636,8 +62631,8 @@ export interface FooocusInpaintInput {
62636
62631
  * Styles
62637
62632
  * @description The style to use.
62638
62633
  * @default [
62639
- * "Fooocus Sharp",
62640
62634
  * "Fooocus V2",
62635
+ * "Fooocus Sharp",
62641
62636
  * "Fooocus Enhance"
62642
62637
  * ]
62643
62638
  */
@@ -62953,10 +62948,10 @@ export interface FooocusImagePromptInput {
62953
62948
  guidance_scale?: number;
62954
62949
  /**
62955
62950
  * @example {
62956
- * "image_url": "https://storage.googleapis.com/falserverless/model_tests/fooocus/Pikachu.webp",
62951
+ * "weight": 1,
62957
62952
  * "stop_at": 1,
62958
62953
  * "type": "PyraCanny",
62959
- * "weight": 1
62954
+ * "image_url": "https://storage.googleapis.com/falserverless/model_tests/fooocus/Pikachu.webp"
62960
62955
  * }
62961
62956
  */
62962
62957
  image_prompt_1: Components.ImagePrompt;
@@ -63087,8 +63082,8 @@ export interface FooocusImagePromptInput {
63087
63082
  * Styles
63088
63083
  * @description The style to use.
63089
63084
  * @default [
63090
- * "Fooocus Sharp",
63091
63085
  * "Fooocus V2",
63086
+ * "Fooocus Sharp",
63092
63087
  * "Fooocus Enhance"
63093
63088
  * ]
63094
63089
  */
@@ -63545,8 +63540,8 @@ export interface FooocusInput {
63545
63540
  * Styles
63546
63541
  * @description The style to use.
63547
63542
  * @default [
63548
- * "Fooocus Sharp",
63549
63543
  * "Fooocus V2",
63544
+ * "Fooocus Sharp",
63550
63545
  * "Fooocus Enhance"
63551
63546
  * ]
63552
63547
  */
@@ -64507,8 +64502,8 @@ export interface FluxVisionUpscalerOutput {
64507
64502
  /**
64508
64503
  * @description The URL of the generated image.
64509
64504
  * @example {
64510
- * "file_size": 8842156,
64511
64505
  * "height": 2048,
64506
+ * "file_size": 8842156,
64512
64507
  * "file_name": "20TZeUQtQ8oKgsCKXSL81_StableSR_00002_.png",
64513
64508
  * "content_type": "image/png",
64514
64509
  * "url": "https://v3b.fal.media/files/b/panda/20TZeUQtQ8oKgsCKXSL81_StableSR_00002_.png",
@@ -67833,6 +67828,70 @@ export interface Flux2LoraOutput {
67833
67828
  };
67834
67829
  }
67835
67830
 
67831
+ export interface Flux2KleinRealtimeInput {
67832
+ /**
67833
+ * Enable Interpolation
67834
+ * @description Enable RIFE frame interpolation between consecutive frames (doubles output frames).
67835
+ * @default false
67836
+ */
67837
+ enable_interpolation?: boolean;
67838
+ /**
67839
+ * Image Size
67840
+ * @description The size of the generated image. square=768x768, square_hd=1024x1024.
67841
+ * @default square
67842
+ * @enum {string}
67843
+ */
67844
+ image_size?: 'square' | 'square_hd';
67845
+ /**
67846
+ * Image URL
67847
+ * @description Base64-encoded image data URI for editing. CDN URLs are not supported for realtime. For optimal performance, use 704x704 JPEG images with 50% quality. Other sizes will be resized automatically.
67848
+ */
67849
+ image_url: string;
67850
+ /**
67851
+ * Num Inference Steps
67852
+ * @default 3
67853
+ */
67854
+ num_inference_steps?: number;
67855
+ /**
67856
+ * Output Feedback Strength
67857
+ * @description Output feedback loop. 1.0 = pure noise (no feedback), 0.9 = 90% noise + 10% previous output latent.
67858
+ * @default 1
67859
+ */
67860
+ output_feedback_strength?: number;
67861
+ /**
67862
+ * Prompt
67863
+ * @description The prompt to guide image editing.
67864
+ * @default Turn this into "Living oil painting, melting gold and sapphire"
67865
+ * @example Turn this into a watercolor painting
67866
+ */
67867
+ prompt?: string;
67868
+ /**
67869
+ * Schedule Mu
67870
+ * @description Schedule mu for time shift. 2.3=default, lower=more even denoising, 0.3=nearly linear.
67871
+ * @default 2.3
67872
+ */
67873
+ schedule_mu?: number;
67874
+ /**
67875
+ * Seed
67876
+ * @description Random seed for reproducibility.
67877
+ * @default 35
67878
+ */
67879
+ seed?: number;
67880
+ }
67881
+
67882
+ export interface Flux2KleinRealtimeOutput {
67883
+ /**
67884
+ * Images
67885
+ * @description Generated images as raw bytes. When interpolation is enabled, returns [interpolated_frame, current_frame] in chronological order. Otherwise returns [current_frame].
67886
+ */
67887
+ images: Components.RawImage[];
67888
+ /**
67889
+ * Seed
67890
+ * @description Seed used for generation.
67891
+ */
67892
+ seed: number;
67893
+ }
67894
+
67836
67895
  export interface Flux2Klein9bLoraInput {
67837
67896
  /**
67838
67897
  * Enable Safety Checker
@@ -71448,15 +71507,15 @@ export interface FloweditOutput {
71448
71507
  seed: number;
71449
71508
  }
71450
71509
 
71451
- export interface Florence2LargeRegionToSegmentationInput extends SharedType_2ff {}
71510
+ export interface Florence2LargeRegionToSegmentationInput extends SharedType_8b7 {}
71452
71511
 
71453
71512
  export interface Florence2LargeRegionToSegmentationOutput extends SharedType_4aa {}
71454
71513
 
71455
- export interface Florence2LargeRegionToDescriptionInput extends SharedType_2ff {}
71514
+ export interface Florence2LargeRegionToDescriptionInput extends SharedType_8b7 {}
71456
71515
 
71457
71516
  export interface Florence2LargeRegionToDescriptionOutput extends SharedType_129 {}
71458
71517
 
71459
- export interface Florence2LargeRegionToCategoryInput extends SharedType_2ff {}
71518
+ export interface Florence2LargeRegionToCategoryInput extends SharedType_8b7 {}
71460
71519
 
71461
71520
  export interface Florence2LargeRegionToCategoryOutput extends SharedType_129 {}
71462
71521
 
@@ -72700,6 +72759,7 @@ export interface FastSdxlInpaintingInput {
72700
72759
  * Seed
72701
72760
  * @description The same seed and the same prompt given to the same version of Stable Diffusion
72702
72761
  * will output the same image every time.
72762
+ * @default null
72703
72763
  */
72704
72764
  seed?: number;
72705
72765
  /**
@@ -72840,6 +72900,7 @@ export interface FastSdxlImageToImageInput {
72840
72900
  * Seed
72841
72901
  * @description The same seed and the same prompt given to the same version of Stable Diffusion
72842
72902
  * will output the same image every time.
72903
+ * @default null
72843
72904
  */
72844
72905
  seed?: number;
72845
72906
  /**
@@ -73287,6 +73348,7 @@ export interface FastSdxlInput {
73287
73348
  * Seed
73288
73349
  * @description The same seed and the same prompt given to the same version of Stable Diffusion
73289
73350
  * will output the same image every time.
73351
+ * @default null
73290
73352
  */
73291
73353
  seed?: number;
73292
73354
  /**
@@ -73604,6 +73666,7 @@ export interface FastLightningSdxlInput {
73604
73666
  * Seed
73605
73667
  * @description The same seed and the same prompt given to the same version of Stable Diffusion
73606
73668
  * will output the same image every time.
73669
+ * @default null
73607
73670
  */
73608
73671
  seed?: number;
73609
73672
  /**
@@ -75489,220 +75552,220 @@ export interface ElevenlabsSpeechToTextScribeV2Output {
75489
75552
  * Words
75490
75553
  * @description Word-level transcription details
75491
75554
  * @example {
75492
- * "text": "Hey,",
75555
+ * "end": 0.539,
75493
75556
  * "start": 0.079,
75494
75557
  * "type": "word",
75495
- * "end": 0.539,
75558
+ * "text": "Hey,",
75496
75559
  * "speaker_id": "speaker_0"
75497
75560
  * }
75498
75561
  * @example {
75499
- * "text": " ",
75562
+ * "end": 0.599,
75500
75563
  * "start": 0.539,
75501
75564
  * "type": "spacing",
75502
- * "end": 0.599,
75565
+ * "text": " ",
75503
75566
  * "speaker_id": "speaker_0"
75504
75567
  * }
75505
75568
  * @example {
75506
- * "text": "this",
75569
+ * "end": 0.679,
75507
75570
  * "start": 0.599,
75508
75571
  * "type": "word",
75509
- * "end": 0.679,
75572
+ * "text": "this",
75510
75573
  * "speaker_id": "speaker_0"
75511
75574
  * }
75512
75575
  * @example {
75513
- * "text": " ",
75576
+ * "end": 0.739,
75514
75577
  * "start": 0.679,
75515
75578
  * "type": "spacing",
75516
- * "end": 0.739,
75579
+ * "text": " ",
75517
75580
  * "speaker_id": "speaker_0"
75518
75581
  * }
75519
75582
  * @example {
75520
- * "text": "is",
75583
+ * "end": 0.799,
75521
75584
  * "start": 0.739,
75522
75585
  * "type": "word",
75523
- * "end": 0.799,
75586
+ * "text": "is",
75524
75587
  * "speaker_id": "speaker_0"
75525
75588
  * }
75526
75589
  * @example {
75527
- * "text": " ",
75590
+ * "end": 0.939,
75528
75591
  * "start": 0.799,
75529
75592
  * "type": "spacing",
75530
- * "end": 0.939,
75593
+ * "text": " ",
75531
75594
  * "speaker_id": "speaker_0"
75532
75595
  * }
75533
75596
  * @example {
75534
- * "text": "a",
75597
+ * "end": 0.939,
75535
75598
  * "start": 0.939,
75536
75599
  * "type": "word",
75537
- * "end": 0.939,
75600
+ * "text": "a",
75538
75601
  * "speaker_id": "speaker_0"
75539
75602
  * }
75540
75603
  * @example {
75541
- * "text": " ",
75604
+ * "end": 0.959,
75542
75605
  * "start": 0.939,
75543
75606
  * "type": "spacing",
75544
- * "end": 0.959,
75607
+ * "text": " ",
75545
75608
  * "speaker_id": "speaker_0"
75546
75609
  * }
75547
75610
  * @example {
75548
- * "text": "test",
75611
+ * "end": 1.179,
75549
75612
  * "start": 0.959,
75550
75613
  * "type": "word",
75551
- * "end": 1.179,
75614
+ * "text": "test",
75552
75615
  * "speaker_id": "speaker_0"
75553
75616
  * }
75554
75617
  * @example {
75555
- * "text": " ",
75618
+ * "end": 1.219,
75556
75619
  * "start": 1.179,
75557
75620
  * "type": "spacing",
75558
- * "end": 1.219,
75621
+ * "text": " ",
75559
75622
  * "speaker_id": "speaker_0"
75560
75623
  * }
75561
75624
  * @example {
75562
- * "text": "recording",
75625
+ * "end": 1.719,
75563
75626
  * "start": 1.22,
75564
75627
  * "type": "word",
75565
- * "end": 1.719,
75628
+ * "text": "recording",
75566
75629
  * "speaker_id": "speaker_0"
75567
75630
  * }
75568
75631
  * @example {
75569
- * "text": " ",
75632
+ * "end": 1.719,
75570
75633
  * "start": 1.719,
75571
75634
  * "type": "spacing",
75572
- * "end": 1.719,
75635
+ * "text": " ",
75573
75636
  * "speaker_id": "speaker_0"
75574
75637
  * }
75575
75638
  * @example {
75576
- * "text": "for",
75639
+ * "end": 1.86,
75577
75640
  * "start": 1.719,
75578
75641
  * "type": "word",
75579
- * "end": 1.86,
75642
+ * "text": "for",
75580
75643
  * "speaker_id": "speaker_0"
75581
75644
  * }
75582
75645
  * @example {
75583
- * "text": " ",
75646
+ * "end": 1.879,
75584
75647
  * "start": 1.86,
75585
75648
  * "type": "spacing",
75586
- * "end": 1.879,
75649
+ * "text": " ",
75587
75650
  * "speaker_id": "speaker_0"
75588
75651
  * }
75589
75652
  * @example {
75590
- * "text": "Scribe",
75653
+ * "end": 2.24,
75591
75654
  * "start": 1.879,
75592
75655
  * "type": "word",
75593
- * "end": 2.24,
75656
+ * "text": "Scribe",
75594
75657
  * "speaker_id": "speaker_0"
75595
75658
  * }
75596
75659
  * @example {
75597
- * "text": " ",
75660
+ * "end": 2.319,
75598
75661
  * "start": 2.24,
75599
75662
  * "type": "spacing",
75600
- * "end": 2.319,
75663
+ * "text": " ",
75601
75664
  * "speaker_id": "speaker_0"
75602
75665
  * }
75603
75666
  * @example {
75604
- * "text": "version",
75667
+ * "end": 2.759,
75605
75668
  * "start": 2.319,
75606
75669
  * "type": "word",
75607
- * "end": 2.759,
75670
+ * "text": "version",
75608
75671
  * "speaker_id": "speaker_0"
75609
75672
  * }
75610
75673
  * @example {
75611
- * "text": " ",
75674
+ * "end": 2.779,
75612
75675
  * "start": 2.759,
75613
75676
  * "type": "spacing",
75614
- * "end": 2.779,
75677
+ * "text": " ",
75615
75678
  * "speaker_id": "speaker_0"
75616
75679
  * }
75617
75680
  * @example {
75618
- * "text": "two,",
75681
+ * "end": 3.379,
75619
75682
  * "start": 2.779,
75620
75683
  * "type": "word",
75621
- * "end": 3.379,
75684
+ * "text": "two,",
75622
75685
  * "speaker_id": "speaker_0"
75623
75686
  * }
75624
75687
  * @example {
75625
- * "text": " ",
75688
+ * "end": 3.399,
75626
75689
  * "start": 3.379,
75627
75690
  * "type": "spacing",
75628
- * "end": 3.399,
75691
+ * "text": " ",
75629
75692
  * "speaker_id": "speaker_0"
75630
75693
  * }
75631
75694
  * @example {
75632
- * "text": "which",
75695
+ * "end": 3.519,
75633
75696
  * "start": 3.399,
75634
75697
  * "type": "word",
75635
- * "end": 3.519,
75698
+ * "text": "which",
75636
75699
  * "speaker_id": "speaker_0"
75637
75700
  * }
75638
75701
  * @example {
75639
- * "text": " ",
75702
+ * "end": 3.539,
75640
75703
  * "start": 3.519,
75641
75704
  * "type": "spacing",
75642
- * "end": 3.539,
75705
+ * "text": " ",
75643
75706
  * "speaker_id": "speaker_0"
75644
75707
  * }
75645
75708
  * @example {
75646
- * "text": "is",
75709
+ * "end": 3.659,
75647
75710
  * "start": 3.539,
75648
75711
  * "type": "word",
75649
- * "end": 3.659,
75712
+ * "text": "is",
75650
75713
  * "speaker_id": "speaker_0"
75651
75714
  * }
75652
75715
  * @example {
75653
- * "text": " ",
75716
+ * "end": 3.699,
75654
75717
  * "start": 3.659,
75655
75718
  * "type": "spacing",
75656
- * "end": 3.699,
75719
+ * "text": " ",
75657
75720
  * "speaker_id": "speaker_0"
75658
75721
  * }
75659
75722
  * @example {
75660
- * "text": "now",
75723
+ * "end": 3.839,
75661
75724
  * "start": 3.699,
75662
75725
  * "type": "word",
75663
- * "end": 3.839,
75726
+ * "text": "now",
75664
75727
  * "speaker_id": "speaker_0"
75665
75728
  * }
75666
75729
  * @example {
75667
- * "text": " ",
75730
+ * "end": 3.839,
75668
75731
  * "start": 3.839,
75669
75732
  * "type": "spacing",
75670
- * "end": 3.839,
75733
+ * "text": " ",
75671
75734
  * "speaker_id": "speaker_0"
75672
75735
  * }
75673
75736
  * @example {
75674
- * "text": "available",
75737
+ * "end": 4.319,
75675
75738
  * "start": 3.839,
75676
75739
  * "type": "word",
75677
- * "end": 4.319,
75740
+ * "text": "available",
75678
75741
  * "speaker_id": "speaker_0"
75679
75742
  * }
75680
75743
  * @example {
75681
- * "text": " ",
75744
+ * "end": 4.339,
75682
75745
  * "start": 4.319,
75683
75746
  * "type": "spacing",
75684
- * "end": 4.339,
75747
+ * "text": " ",
75685
75748
  * "speaker_id": "speaker_0"
75686
75749
  * }
75687
75750
  * @example {
75688
- * "text": "on",
75751
+ * "end": 4.579,
75689
75752
  * "start": 4.339,
75690
75753
  * "type": "word",
75691
- * "end": 4.579,
75754
+ * "text": "on",
75692
75755
  * "speaker_id": "speaker_0"
75693
75756
  * }
75694
75757
  * @example {
75695
- * "text": " ",
75758
+ * "end": 4.599,
75696
75759
  * "start": 4.579,
75697
75760
  * "type": "spacing",
75698
- * "end": 4.599,
75761
+ * "text": " ",
75699
75762
  * "speaker_id": "speaker_0"
75700
75763
  * }
75701
75764
  * @example {
75702
- * "text": "fal.ai.",
75765
+ * "end": 5.699,
75703
75766
  * "start": 4.599,
75704
75767
  * "type": "word",
75705
- * "end": 5.699,
75768
+ * "text": "fal.ai.",
75706
75769
  * "speaker_id": "speaker_0"
75707
75770
  * }
75708
75771
  */
@@ -76996,51 +77059,6 @@ export interface Deepfilternet3Output {
76996
77059
  timings: Components.DeepFilterNetTimings;
76997
77060
  }
76998
77061
 
76999
- export interface DecartLucy5bImageToVideoInput {
77000
- /**
77001
- * Aspect Ratio
77002
- * @description Aspect ratio of the generated video.
77003
- * @default 16:9
77004
- * @enum {string}
77005
- */
77006
- aspect_ratio?: '9:16' | '16:9';
77007
- /**
77008
- * Image Url
77009
- * @description URL of the image to use as the first frame
77010
- * @example https://v3.fal.media/files/monkey/OlpQEYh7oNeJ3qKsdiaym_ia5ECOgFbfcniMDu01_18_da73e078e0924472b51d92f3e3fba98c.png
77011
- */
77012
- image_url: string;
77013
- /**
77014
- * Prompt
77015
- * @description Text description of the desired video content
77016
- * @example A cat is walking slowly in the garden
77017
- */
77018
- prompt: string;
77019
- /**
77020
- * Resolution
77021
- * @description Resolution of the generated video
77022
- * @default 720p
77023
- * @constant
77024
- */
77025
- resolution?: '720p';
77026
- /**
77027
- * Sync Mode
77028
- * @description If `True`, the media will be returned as a data URI and the output data won't be available in the request history.
77029
- * @default true
77030
- */
77031
- sync_mode?: boolean;
77032
- }
77033
-
77034
- export interface DecartLucy5bImageToVideoOutput {
77035
- /**
77036
- * @description The generated MP4 video with H.264 encoding
77037
- * @example {
77038
- * "url": "https://v3.fal.media/files/kangaroo/rIFaCsyWvBxYBKw3cPbOU_indir.mp4"
77039
- * }
77040
- */
77041
- video: Components.File;
77042
- }
77043
-
77044
77062
  export interface DdcolorInput {
77045
77063
  /**
77046
77064
  * Image Url
@@ -77840,7 +77858,7 @@ export interface Cogvideox5bVideoToVideoInput {
77840
77858
  video_url: string;
77841
77859
  }
77842
77860
 
77843
- export interface Cogvideox5bVideoToVideoOutput extends SharedType_1001 {}
77861
+ export interface Cogvideox5bVideoToVideoOutput extends SharedType_100 {}
77844
77862
 
77845
77863
  export interface Cogvideox5bImageToVideoInput {
77846
77864
  /**
@@ -77919,7 +77937,7 @@ export interface Cogvideox5bImageToVideoInput {
77919
77937
  );
77920
77938
  }
77921
77939
 
77922
- export interface Cogvideox5bImageToVideoOutput extends SharedType_1001 {}
77940
+ export interface Cogvideox5bImageToVideoOutput extends SharedType_100 {}
77923
77941
 
77924
77942
  export interface Cogvideox5bInput {
77925
77943
  /**
@@ -77992,7 +78010,7 @@ export interface Cogvideox5bInput {
77992
78010
  );
77993
78011
  }
77994
78012
 
77995
- export interface Cogvideox5bOutput extends SharedType_1001 {}
78013
+ export interface Cogvideox5bOutput extends SharedType_100 {}
77996
78014
 
77997
78015
  export interface CodeformerInput {
77998
78016
  /**
@@ -78042,8 +78060,8 @@ export interface CodeformerOutput {
78042
78060
  /**
78043
78061
  * @description The generated image file info.
78044
78062
  * @example {
78045
- * "height": 512,
78046
78063
  * "file_size": 423052,
78064
+ * "height": 512,
78047
78065
  * "file_name": "36d3ca4791a647678b2ff01a35c87f5a.png",
78048
78066
  * "content_type": "image/png",
78049
78067
  * "url": "https://storage.googleapis.com/falserverless/model_tests/codeformer/codeformer_restored_1.jpeg",
@@ -78899,95 +78917,6 @@ export interface CartoonifyInput {
78899
78917
 
78900
78918
  export interface CartoonifyOutput extends SharedType_7c6 {}
78901
78919
 
78902
- export interface CalligrapherInput {
78903
- /**
78904
- * Auto Mask Generation
78905
- * @description Whether to automatically generate mask from detected text
78906
- * @default false
78907
- */
78908
- auto_mask_generation?: boolean;
78909
- /**
78910
- * Cfg Scale
78911
- * @description Guidance or strength scale for the model
78912
- * @default 1
78913
- */
78914
- cfg_scale?: number;
78915
- /**
78916
- * Image Size
78917
- * @description Target image size for generation
78918
- * @default {
78919
- * "height": 1024,
78920
- * "width": 1024
78921
- * }
78922
- */
78923
- image_size?:
78924
- | Components.ImageSize
78925
- | (
78926
- | 'square_hd'
78927
- | 'square'
78928
- | 'portrait_4_3'
78929
- | 'portrait_16_9'
78930
- | 'landscape_4_3'
78931
- | 'landscape_16_9'
78932
- );
78933
- /**
78934
- * Mask Image Url
78935
- * @description Base64-encoded mask image (optional if using auto_mask_generation)
78936
- * @example https://storage.googleapis.com/falserverless/calligrapher/test17_mask.png
78937
- */
78938
- mask_image_url?: string;
78939
- /**
78940
- * Num Images
78941
- * @description How many images to generate
78942
- * @default 1
78943
- */
78944
- num_images?: number;
78945
- /**
78946
- * Num Inference Steps
78947
- * @description Number of inference steps (1-100)
78948
- * @default 50
78949
- */
78950
- num_inference_steps?: number;
78951
- /**
78952
- * Prompt
78953
- * @description Text prompt to inpaint or customize
78954
- * @example The text is 'Rise'
78955
- */
78956
- prompt: string;
78957
- /**
78958
- * Reference Image Url
78959
- * @description Optional base64 reference image for style
78960
- */
78961
- reference_image_url?: string;
78962
- /**
78963
- * Seed
78964
- * @description Random seed for reproducibility
78965
- */
78966
- seed?: number;
78967
- /**
78968
- * Source Image Url
78969
- * @description Base64-encoded source image with drawn mask layers
78970
- * @example https://storage.googleapis.com/falserverless/calligrapher/test17_source.png
78971
- */
78972
- source_image_url: string;
78973
- /**
78974
- * Source Text
78975
- * @description Source text to replace (if empty, masks all detected text)
78976
- * @default
78977
- */
78978
- source_text?: string;
78979
- /**
78980
- * Use Context
78981
- * @description Whether to prepend context reference to the input
78982
- * @default true
78983
- */
78984
- use_context?: boolean;
78985
- }
78986
-
78987
- export interface CalligrapherOutput {
78988
- images: Components.Image[];
78989
- }
78990
-
78991
78920
  export interface BytedanceVideoStylizeInput {
78992
78921
  /**
78993
78922
  * Image Url
@@ -80223,6 +80152,84 @@ export interface BytedanceSeedanceV15ProImageToVideoOutput {
80223
80152
  video: Components.File;
80224
80153
  }
80225
80154
 
80155
+ export interface BytedanceSeedV2MiniInput {
80156
+ /**
80157
+ * Image Urls
80158
+ * @description URLs of images for visual understanding. Supported formats: JPEG, PNG, WebP. A maximum of 6 images is supported. Any additional images will be ignored.
80159
+ */
80160
+ image_urls?: string[];
80161
+ /**
80162
+ * Max Completion Tokens
80163
+ * @description Controls the maximum length of the model's output, including both the model's response and its chain-of-thought content, measured in tokens.
80164
+ * @default 4096
80165
+ */
80166
+ max_completion_tokens?: number;
80167
+ /**
80168
+ * Messages
80169
+ * @description Optional prior conversation history for multi-turn conversations. Pass back the `messages` field from a previous response to provide context. The current `prompt`, `image_urls`, `video_urls`, and `system_prompt` are always appended as the latest user turn.
80170
+ * @example []
80171
+ */
80172
+ messages?: Components.Seed2MiniMessage[];
80173
+ /**
80174
+ * Prompt
80175
+ * @description The text prompt or question for the model.
80176
+ * @example What can you do?
80177
+ */
80178
+ prompt: string;
80179
+ /**
80180
+ * Reasoning Effort
80181
+ * @description Controls the depth of reasoning before the model responds. Only applicable when `thinking` is `enabled` or `auto`. `minimal` for immediate response, `low` for faster response with light reasoning, `medium` for balanced speed and depth, `high` for deep analysis of complex issues.
80182
+ */
80183
+ reasoning_effort?: 'minimal' | 'low' | 'medium' | 'high';
80184
+ /**
80185
+ * System Prompt
80186
+ * @description Optional system prompt to guide the model's behavior.
80187
+ */
80188
+ system_prompt?: string;
80189
+ /**
80190
+ * Temperature
80191
+ * @description Controls randomness in the response. Lower values make output more focused and deterministic, higher values make it more creative.
80192
+ * @default 1
80193
+ */
80194
+ temperature?: number;
80195
+ /**
80196
+ * Thinking
80197
+ * @description Controls the model's chain-of-thought reasoning. `enabled` always includes reasoning, `disabled` never includes reasoning, `auto` lets the model decide based on the query.
80198
+ * @default enabled
80199
+ * @enum {string}
80200
+ */
80201
+ thinking?: 'enabled' | 'disabled' | 'auto';
80202
+ /**
80203
+ * Top P
80204
+ * @description Nucleus sampling parameter. The model considers tokens with top_p cumulative probability mass. Lower values narrow the token selection.
80205
+ * @default 0.7
80206
+ */
80207
+ top_p?: number;
80208
+ /**
80209
+ * Video Urls
80210
+ * @description URLs of videos for video understanding. Supported formats: MP4, MOV. Audio comprehension is not supported. A maximum of 3 videos is supported. Any additional videos will be ignored.
80211
+ */
80212
+ video_urls?: string[];
80213
+ }
80214
+
80215
+ export interface BytedanceSeedV2MiniOutput {
80216
+ /**
80217
+ * Messages
80218
+ * @description The full conversation history including the model's response. Pass this back as the `messages` input field to continue the conversation.
80219
+ */
80220
+ messages: Components.Seed2MiniMessage[];
80221
+ /**
80222
+ * Output
80223
+ * @description The model's text response.
80224
+ */
80225
+ output: string;
80226
+ /**
80227
+ * Reasoning Content
80228
+ * @description The model's chain-of-thought reasoning content. Only present when `thinking` is `enabled` or `auto`.
80229
+ */
80230
+ reasoning_content?: string;
80231
+ }
80232
+
80226
80233
  export interface BytedanceOmnihumanV15Input {
80227
80234
  /**
80228
80235
  * Audio Url
@@ -80441,7 +80448,7 @@ export interface BytedanceUpscalerUpscaleVideoOutput {
80441
80448
 
80442
80449
  export interface BriaTextToImageHdInput extends SharedType_411 {}
80443
80450
 
80444
- export interface BriaTextToImageHdOutput extends SharedType_a97 {}
80451
+ export interface BriaTextToImageHdOutput extends SharedType_e19 {}
80445
80452
 
80446
80453
  export interface BriaTextToImageFastInput {
80447
80454
  /**
@@ -80514,11 +80521,11 @@ export interface BriaTextToImageFastInput {
80514
80521
  sync_mode?: boolean;
80515
80522
  }
80516
80523
 
80517
- export interface BriaTextToImageFastOutput extends SharedType_a97 {}
80524
+ export interface BriaTextToImageFastOutput extends SharedType_e19 {}
80518
80525
 
80519
80526
  export interface BriaTextToImageBaseInput extends SharedType_411 {}
80520
80527
 
80521
- export interface BriaTextToImageBaseOutput extends SharedType_a97 {}
80528
+ export interface BriaTextToImageBaseOutput extends SharedType_e19 {}
80522
80529
 
80523
80530
  export interface BriaReimagineInput {
80524
80531
  /**
@@ -80747,8 +80754,8 @@ export interface BriaGenfillOutput {
80747
80754
  * @description Generated Images
80748
80755
  * @example [
80749
80756
  * {
80750
- * "file_size": 1064550,
80751
80757
  * "height": 768,
80758
+ * "file_size": 1064550,
80752
80759
  * "file_name": "a0d138e6820c4ad58f1fd3c758f16047.png",
80753
80760
  * "content_type": "image/png",
80754
80761
  * "url": "https://storage.googleapis.com/falserverless/bria/bria_genfill_res.png",
@@ -80832,8 +80839,8 @@ export interface BriaExpandOutput {
80832
80839
  /**
80833
80840
  * @description The generated image
80834
80841
  * @example {
80835
- * "file_size": 1471342,
80836
80842
  * "height": 674,
80843
+ * "file_size": 1471342,
80837
80844
  * "file_name": "afa402a35ea742cdb5c3e219b2b19bfb.png",
80838
80845
  * "content_type": "image/png",
80839
80846
  * "url": "https://v3.fal.media/files/koala/8np-spgxxG-I1r3cjthRV_afa402a35ea742cdb5c3e219b2b19bfb.png",
@@ -80989,8 +80996,8 @@ export interface BriaBackgroundRemoveOutput {
80989
80996
  /**
80990
80997
  * @description The generated image
80991
80998
  * @example {
80992
- * "file_size": 1076276,
80993
80999
  * "height": 1024,
81000
+ * "file_size": 1076276,
80994
81001
  * "file_name": "070c731993e949d993c10ef6283d335d.png",
80995
81002
  * "content_type": "image/png",
80996
81003
  * "url": "https://v3.fal.media/files/tiger/GQEMNjRyxSoza7N8LPPqb_070c731993e949d993c10ef6283d335d.png",
@@ -81189,8 +81196,8 @@ export interface BirefnetV2VideoOutput {
81189
81196
  * "height": 1080,
81190
81197
  * "duration": 8,
81191
81198
  * "url": "https://storage.googleapis.com/falserverless/example_outputs/birefnet-video-output.webm",
81192
- * "width": 1920,
81193
81199
  * "fps": 24,
81200
+ * "width": 1920,
81194
81201
  * "file_name": "birefnet-video-output.webm",
81195
81202
  * "num_frames": 192,
81196
81203
  * "content_type": "video/webm"
@@ -83156,8 +83163,8 @@ export interface ClarityaiCrystalVideoUpscalerOutput {
83156
83163
  * "width": 4096,
83157
83164
  * "fps": 23.130193905817176,
83158
83165
  * "file_name": "w0VQQvPdwvV2GSCtRTMzh_hDH8SPrB.mp4",
83159
- * "content_type": "video/mp4",
83160
- * "num_frames": 302
83166
+ * "num_frames": 302,
83167
+ * "content_type": "video/mp4"
83161
83168
  * }
83162
83169
  */
83163
83170
  video: Components.VideoFile;