fal-endpoint-types 1.3.35 → 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.
@@ -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
@@ -11737,240 +11745,220 @@ export interface SharedType_304 {
11737
11745
  voice: Components.TextVoice;
11738
11746
  }
11739
11747
 
11740
- export interface SharedType_2ff {
11748
+ export interface SharedType_2e6 {
11741
11749
  /**
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
11750
+ * Aspect Ratio
11751
+ * @description The aspect ratio of the video.
11752
+ * @default auto
11753
+ * @example auto
11754
+ * @enum {string}
11755
+ */
11756
+ aspect_ratio?: '9:16' | '1:1' | '16:9' | 'auto';
11757
+ /**
11758
+ * Constant Rate Factor
11759
+ * @description The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.
11760
+ * @default 29
11761
+ * @example 29
11762
+ */
11763
+ constant_rate_factor?: number;
11764
+ /**
11765
+ * Enable Detail Pass
11766
+ * @description Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.
11767
+ * @default false
11768
+ * @example false
11769
+ */
11770
+ enable_detail_pass?: boolean;
11771
+ /**
11772
+ * Enable Safety Checker
11773
+ * @description Whether to enable the safety checker.
11774
+ * @default true
11775
+ * @example true
11776
+ */
11777
+ enable_safety_checker?: boolean;
11778
+ /**
11779
+ * Expand Prompt
11780
+ * @description Whether to expand the prompt using a language model.
11781
+ * @default false
11782
+ * @example false
11783
+ */
11784
+ expand_prompt?: boolean;
11785
+ /**
11786
+ * Number of Inference Steps
11787
+ * @description Number of inference steps during the first pass.
11788
+ * @default 8
11789
+ * @example 8
11790
+ */
11791
+ first_pass_num_inference_steps?: number;
11792
+ /**
11793
+ * Frame Rate
11794
+ * @description The frame rate of the video.
11795
+ * @default 24
11796
+ * @example 24
11797
+ */
11798
+ frame_rate?: number;
11799
+ /**
11800
+ * Image URL
11801
+ * @description Image URL for Image-to-Video task
11802
+ * @example https://storage.googleapis.com/falserverless/example_inputs/ltxv-image-input.jpg
11746
11803
  */
11747
11804
  image_url: string;
11748
11805
  /**
11749
- * @description The user input coordinates
11806
+ * Loras
11807
+ * @description LoRA weights to use for generation
11808
+ * @default []
11809
+ */
11810
+ loras?: Components.LoRAWeight[];
11811
+ /**
11812
+ * Negative Prompt
11813
+ * @description Negative prompt for generation
11814
+ * @default worst quality, inconsistent motion, blurry, jittery, distorted
11815
+ */
11816
+ negative_prompt?: string;
11817
+ /**
11818
+ * Number of Frames
11819
+ * @description The number of frames in the video.
11820
+ * @default 121
11821
+ * @example 121
11822
+ */
11823
+ num_frames?: number;
11824
+ /**
11825
+ * Prompt
11826
+ * @description Text prompt to guide generation
11827
+ * @example The astronaut gets up and walks away
11828
+ */
11829
+ prompt: string;
11830
+ /**
11831
+ * Resolution
11832
+ * @description Resolution of the generated video.
11833
+ * @default 720p
11834
+ * @example 720p
11835
+ * @enum {string}
11836
+ */
11837
+ resolution?: '480p' | '720p';
11838
+ /**
11839
+ * Reverse Video
11840
+ * @description Whether to reverse the video.
11841
+ * @default false
11842
+ * @example false
11843
+ */
11844
+ reverse_video?: boolean;
11845
+ /**
11846
+ * Second Pass Number of Inference Steps
11847
+ * @description Number of inference steps during the second pass.
11848
+ * @default 8
11849
+ * @example 8
11850
+ */
11851
+ second_pass_num_inference_steps?: number;
11852
+ /**
11853
+ * Second Pass Skip Initial Steps
11854
+ * @description The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.
11855
+ * @default 5
11856
+ * @example 5
11857
+ */
11858
+ second_pass_skip_initial_steps?: number;
11859
+ /**
11860
+ * Seed
11861
+ * @description Random seed for generation
11862
+ */
11863
+ seed?: number;
11864
+ /**
11865
+ * Temporal AdaIN Factor
11866
+ * @description The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.
11867
+ * @default 0.5
11868
+ * @example 0.5
11869
+ */
11870
+ temporal_adain_factor?: number;
11871
+ /**
11872
+ * Tone Map Compression Ratio
11873
+ * @description The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.
11874
+ * @default 0
11875
+ * @example 0
11876
+ */
11877
+ tone_map_compression_ratio?: number;
11878
+ }
11879
+
11880
+ export interface SharedType_2db {
11881
+ /**
11882
+ * Enable Safety Checker
11883
+ * @description If set to true, the safety checker will be enabled.
11884
+ * @default true
11885
+ */
11886
+ enable_safety_checker?: boolean;
11887
+ /**
11888
+ * Image Size
11889
+ * @description The size of the generated image. If not provided, uses the input image size.
11750
11890
  * @example {
11751
- * "y2": 200,
11752
- * "x2": 200,
11753
- * "x1": 100,
11754
- * "y1": 100
11891
+ * "height": 1152,
11892
+ * "width": 2016
11755
11893
  * }
11756
11894
  */
11757
- region: Components.Region;
11895
+ image_size?:
11896
+ | Components.ImageSize
11897
+ | (
11898
+ | 'square_hd'
11899
+ | 'square'
11900
+ | 'portrait_4_3'
11901
+ | 'portrait_16_9'
11902
+ | 'landscape_4_3'
11903
+ | 'landscape_16_9'
11904
+ );
11905
+ /**
11906
+ * Image URLs
11907
+ * @description The URLs of the images for editing. A maximum of 4 images are allowed.
11908
+ * @example [
11909
+ * "https://v3b.fal.media/files/b/0a8a69d5/kkXxFfj1QeVtw35kxy5Py_1a7e3511-bd2c-46be-923a-8e6be2496f12.png"
11910
+ * ]
11911
+ */
11912
+ image_urls: string[];
11913
+ /**
11914
+ * Number of Images
11915
+ * @description The number of images to generate.
11916
+ * @default 1
11917
+ */
11918
+ num_images?: number;
11919
+ /**
11920
+ * Number of Inference Steps
11921
+ * @description The number of inference steps to perform.
11922
+ * @default 4
11923
+ */
11924
+ num_inference_steps?: number;
11925
+ /**
11926
+ * Output Format
11927
+ * @description The format of the generated image.
11928
+ * @default png
11929
+ * @enum {string}
11930
+ */
11931
+ output_format?: 'jpeg' | 'png' | 'webp';
11932
+ /**
11933
+ * Prompt
11934
+ * @description The prompt to edit the image.
11935
+ * @example Turn this into a realistic image
11936
+ */
11937
+ prompt: string;
11938
+ /**
11939
+ * Seed
11940
+ * @description The seed to use for the generation. If not provided, a random seed will be used.
11941
+ */
11942
+ seed?: number;
11943
+ /**
11944
+ * Sync Mode
11945
+ * @description If `True`, the media will be returned as a data URI. Output is not stored when this is True.
11946
+ * @default false
11947
+ */
11948
+ sync_mode?: boolean;
11758
11949
  }
11759
11950
 
11760
- export interface SharedType_2e6 {
11761
- /**
11762
- * Aspect Ratio
11763
- * @description The aspect ratio of the video.
11764
- * @default auto
11765
- * @example auto
11766
- * @enum {string}
11767
- */
11768
- aspect_ratio?: '9:16' | '1:1' | '16:9' | 'auto';
11769
- /**
11770
- * Constant Rate Factor
11771
- * @description The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.
11772
- * @default 29
11773
- * @example 29
11774
- */
11775
- constant_rate_factor?: number;
11776
- /**
11777
- * Enable Detail Pass
11778
- * @description Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.
11779
- * @default false
11780
- * @example false
11781
- */
11782
- enable_detail_pass?: boolean;
11783
- /**
11784
- * Enable Safety Checker
11785
- * @description Whether to enable the safety checker.
11786
- * @default true
11787
- * @example true
11788
- */
11789
- enable_safety_checker?: boolean;
11790
- /**
11791
- * Expand Prompt
11792
- * @description Whether to expand the prompt using a language model.
11793
- * @default false
11794
- * @example false
11795
- */
11796
- expand_prompt?: boolean;
11797
- /**
11798
- * Number of Inference Steps
11799
- * @description Number of inference steps during the first pass.
11800
- * @default 8
11801
- * @example 8
11802
- */
11803
- first_pass_num_inference_steps?: number;
11804
- /**
11805
- * Frame Rate
11806
- * @description The frame rate of the video.
11807
- * @default 24
11808
- * @example 24
11809
- */
11810
- frame_rate?: number;
11811
- /**
11812
- * Image URL
11813
- * @description Image URL for Image-to-Video task
11814
- * @example https://storage.googleapis.com/falserverless/example_inputs/ltxv-image-input.jpg
11815
- */
11816
- image_url: string;
11817
- /**
11818
- * Loras
11819
- * @description LoRA weights to use for generation
11820
- * @default []
11821
- */
11822
- loras?: Components.LoRAWeight[];
11823
- /**
11824
- * Negative Prompt
11825
- * @description Negative prompt for generation
11826
- * @default worst quality, inconsistent motion, blurry, jittery, distorted
11827
- */
11828
- negative_prompt?: string;
11829
- /**
11830
- * Number of Frames
11831
- * @description The number of frames in the video.
11832
- * @default 121
11833
- * @example 121
11834
- */
11835
- num_frames?: number;
11836
- /**
11837
- * Prompt
11838
- * @description Text prompt to guide generation
11839
- * @example The astronaut gets up and walks away
11840
- */
11841
- prompt: string;
11842
- /**
11843
- * Resolution
11844
- * @description Resolution of the generated video.
11845
- * @default 720p
11846
- * @example 720p
11847
- * @enum {string}
11848
- */
11849
- resolution?: '480p' | '720p';
11850
- /**
11851
- * Reverse Video
11852
- * @description Whether to reverse the video.
11853
- * @default false
11854
- * @example false
11855
- */
11856
- reverse_video?: boolean;
11857
- /**
11858
- * Second Pass Number of Inference Steps
11859
- * @description Number of inference steps during the second pass.
11860
- * @default 8
11861
- * @example 8
11862
- */
11863
- second_pass_num_inference_steps?: number;
11864
- /**
11865
- * Second Pass Skip Initial Steps
11866
- * @description The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.
11867
- * @default 5
11868
- * @example 5
11869
- */
11870
- second_pass_skip_initial_steps?: number;
11871
- /**
11872
- * Seed
11873
- * @description Random seed for generation
11874
- */
11875
- seed?: number;
11876
- /**
11877
- * Temporal AdaIN Factor
11878
- * @description The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.
11879
- * @default 0.5
11880
- * @example 0.5
11881
- */
11882
- temporal_adain_factor?: number;
11883
- /**
11884
- * Tone Map Compression Ratio
11885
- * @description The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.
11886
- * @default 0
11887
- * @example 0
11888
- */
11889
- tone_map_compression_ratio?: number;
11890
- }
11891
-
11892
- export interface SharedType_2db {
11893
- /**
11894
- * Enable Safety Checker
11895
- * @description If set to true, the safety checker will be enabled.
11896
- * @default true
11897
- */
11898
- enable_safety_checker?: boolean;
11899
- /**
11900
- * Image Size
11901
- * @description The size of the generated image. If not provided, uses the input image size.
11902
- * @example {
11903
- * "height": 1152,
11904
- * "width": 2016
11905
- * }
11906
- */
11907
- image_size?:
11908
- | Components.ImageSize
11909
- | (
11910
- | 'square_hd'
11911
- | 'square'
11912
- | 'portrait_4_3'
11913
- | 'portrait_16_9'
11914
- | 'landscape_4_3'
11915
- | 'landscape_16_9'
11916
- );
11917
- /**
11918
- * Image URLs
11919
- * @description The URLs of the images for editing. A maximum of 4 images are allowed.
11920
- * @example [
11921
- * "https://v3b.fal.media/files/b/0a8a69d5/kkXxFfj1QeVtw35kxy5Py_1a7e3511-bd2c-46be-923a-8e6be2496f12.png"
11922
- * ]
11923
- */
11924
- image_urls: string[];
11925
- /**
11926
- * Number of Images
11927
- * @description The number of images to generate.
11928
- * @default 1
11929
- */
11930
- num_images?: number;
11931
- /**
11932
- * Number of Inference Steps
11933
- * @description The number of inference steps to perform.
11934
- * @default 4
11935
- */
11936
- num_inference_steps?: number;
11937
- /**
11938
- * Output Format
11939
- * @description The format of the generated image.
11940
- * @default png
11941
- * @enum {string}
11942
- */
11943
- output_format?: 'jpeg' | 'png' | 'webp';
11944
- /**
11945
- * Prompt
11946
- * @description The prompt to edit the image.
11947
- * @example Turn this into a realistic image
11948
- */
11949
- prompt: string;
11950
- /**
11951
- * Seed
11952
- * @description The seed to use for the generation. If not provided, a random seed will be used.
11953
- */
11954
- seed?: number;
11955
- /**
11956
- * Sync Mode
11957
- * @description If `True`, the media will be returned as a data URI. Output is not stored when this is True.
11958
- * @default false
11959
- */
11960
- sync_mode?: boolean;
11961
- }
11962
-
11963
- export interface SharedType_2d61 {
11964
- /**
11965
- * @description URL of the reframed video
11966
- * @example {
11967
- * "url": "https://v3.fal.media/files/lion/L9nkXSW1MCj2oDimeJ4w5_output.mp4"
11968
- * }
11969
- */
11970
- video: Components.File;
11971
- }
11972
-
11973
- export interface SharedType_2d6 {
11951
+ export interface SharedType_2d61 {
11952
+ /**
11953
+ * @description URL of the reframed video
11954
+ * @example {
11955
+ * "url": "https://v3.fal.media/files/lion/L9nkXSW1MCj2oDimeJ4w5_output.mp4"
11956
+ * }
11957
+ */
11958
+ video: Components.File;
11959
+ }
11960
+
11961
+ export interface SharedType_2d6 {
11974
11962
  /**
11975
11963
  * Aspect Ratio
11976
11964
  * @description The aspect ratio of the video.
@@ -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.
@@ -13006,6 +13023,148 @@ export interface SharedType_151 {
13006
13023
  seed: number;
13007
13024
  }
13008
13025
 
13026
+ export interface SharedType_133 {
13027
+ /**
13028
+ * Aspect Ratio
13029
+ * @description The aspect ratio of the video.
13030
+ * @default auto
13031
+ * @example auto
13032
+ * @enum {string}
13033
+ */
13034
+ aspect_ratio?: '9:16' | '1:1' | '16:9' | 'auto';
13035
+ /**
13036
+ * Constant Rate Factor
13037
+ * @description The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.
13038
+ * @default 29
13039
+ * @example 29
13040
+ */
13041
+ constant_rate_factor?: number;
13042
+ /**
13043
+ * Enable Detail Pass
13044
+ * @description Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.
13045
+ * @default false
13046
+ * @example false
13047
+ */
13048
+ enable_detail_pass?: boolean;
13049
+ /**
13050
+ * Enable Safety Checker
13051
+ * @description Whether to enable the safety checker.
13052
+ * @default true
13053
+ * @example true
13054
+ */
13055
+ enable_safety_checker?: boolean;
13056
+ /**
13057
+ * Expand Prompt
13058
+ * @description Whether to expand the prompt using a language model.
13059
+ * @default false
13060
+ * @example false
13061
+ */
13062
+ expand_prompt?: boolean;
13063
+ /**
13064
+ * Number of Inference Steps
13065
+ * @description Number of inference steps during the first pass.
13066
+ * @default 8
13067
+ * @example 8
13068
+ */
13069
+ first_pass_num_inference_steps?: number;
13070
+ /**
13071
+ * Frame Rate
13072
+ * @description The frame rate of the video.
13073
+ * @default 24
13074
+ * @example 24
13075
+ */
13076
+ frame_rate?: number;
13077
+ /**
13078
+ * Loras
13079
+ * @description LoRA weights to use for generation
13080
+ * @default []
13081
+ */
13082
+ loras?: Components.LoRAWeight[];
13083
+ /**
13084
+ * Negative Prompt
13085
+ * @description Negative prompt for generation
13086
+ * @default worst quality, inconsistent motion, blurry, jittery, distorted
13087
+ */
13088
+ negative_prompt?: string;
13089
+ /**
13090
+ * Number of Frames
13091
+ * @description The number of frames in the video.
13092
+ * @default 121
13093
+ * @example 121
13094
+ */
13095
+ num_frames?: number;
13096
+ /**
13097
+ * Prompt
13098
+ * @description Text prompt to guide generation
13099
+ * @example Woman walking on a street in Tokyo
13100
+ */
13101
+ prompt: string;
13102
+ /**
13103
+ * Resolution
13104
+ * @description Resolution of the generated video.
13105
+ * @default 720p
13106
+ * @example 720p
13107
+ * @enum {string}
13108
+ */
13109
+ resolution?: '480p' | '720p';
13110
+ /**
13111
+ * Reverse Video
13112
+ * @description Whether to reverse the video.
13113
+ * @default false
13114
+ * @example false
13115
+ */
13116
+ reverse_video?: boolean;
13117
+ /**
13118
+ * Second Pass Number of Inference Steps
13119
+ * @description Number of inference steps during the second pass.
13120
+ * @default 8
13121
+ * @example 8
13122
+ */
13123
+ second_pass_num_inference_steps?: number;
13124
+ /**
13125
+ * Second Pass Skip Initial Steps
13126
+ * @description The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.
13127
+ * @default 5
13128
+ * @example 5
13129
+ */
13130
+ second_pass_skip_initial_steps?: number;
13131
+ /**
13132
+ * Seed
13133
+ * @description Random seed for generation
13134
+ */
13135
+ seed?: number;
13136
+ /**
13137
+ * Temporal AdaIN Factor
13138
+ * @description The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.
13139
+ * @default 0.5
13140
+ * @example 0.5
13141
+ */
13142
+ temporal_adain_factor?: number;
13143
+ /**
13144
+ * Tone Map Compression Ratio
13145
+ * @description The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.
13146
+ * @default 0
13147
+ * @example 0
13148
+ */
13149
+ tone_map_compression_ratio?: number;
13150
+ /**
13151
+ * @description Video to be extended.
13152
+ * @example {
13153
+ * "video_url": "https://storage.googleapis.com/falserverless/web-examples/wan/t2v.mp4",
13154
+ * "start_frame_num": 0,
13155
+ * "reverse_video": false,
13156
+ * "limit_num_frames": false,
13157
+ * "resample_fps": false,
13158
+ * "strength": 1,
13159
+ * "target_fps": 24,
13160
+ * "max_num_frames": 1441,
13161
+ * "conditioning_type": "rgb",
13162
+ * "preprocess": false
13163
+ * }
13164
+ */
13165
+ video: Components.ExtendVideoConditioningInput;
13166
+ }
13167
+
13009
13168
  export interface SharedType_129 {
13010
13169
  /**
13011
13170
  * Results
@@ -13014,7 +13173,7 @@ export interface SharedType_129 {
13014
13173
  results: string;
13015
13174
  }
13016
13175
 
13017
- export interface SharedType_1001 {
13176
+ export interface SharedType_100 {
13018
13177
  /**
13019
13178
  * Prompt
13020
13179
  * @description The prompt used for generating the video.
@@ -13032,38 +13191,6 @@ export interface SharedType_1001 {
13032
13191
  video: Components.File;
13033
13192
  }
13034
13193
 
13035
- export interface SharedType_100 {
13036
- /**
13037
- * Masks
13038
- * @description Dictionary of label: mask image
13039
- * @example [
13040
- * {
13041
- * "file_size": 15724,
13042
- * "height": 1200,
13043
- * "file_name": "019c3c1e3c50446e9996f709d36debb4.png",
13044
- * "content_type": "image/png",
13045
- * "url": "https://v3.fal.media/files/monkey/6ITmhHQJ-69s-UxajrY5T_019c3c1e3c50446e9996f709d36debb4.png",
13046
- * "width": 1800
13047
- * },
13048
- * {
13049
- * "file_size": 14905,
13050
- * "height": 1200,
13051
- * "file_name": "0a1522ca410942c7ad6c73efa15b3549.png",
13052
- * "content_type": "image/png",
13053
- * "url": "https://v3.fal.media/files/monkey/IljtMxahoo9-7SUpx0fth_0a1522ca410942c7ad6c73efa15b3549.png",
13054
- * "width": 1800
13055
- * }
13056
- * ]
13057
- */
13058
- masks: Components.Image[];
13059
- /**
13060
- * Output
13061
- * @description Generated output
13062
- * @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|>
13063
- */
13064
- output: string;
13065
- }
13066
-
13067
13194
  export interface SharedType_0ff {
13068
13195
  /**
13069
13196
  * @description The generated speaker embedding file in safetensors format.
@@ -14537,9 +14664,9 @@ export interface OpenrouterRouterVisionOutput {
14537
14664
  /**
14538
14665
  * @description Token usage information
14539
14666
  * @example {
14540
- * "prompt_tokens": 1340,
14541
- * "total_tokens": 1403,
14542
14667
  * "completion_tokens": 63,
14668
+ * "total_tokens": 1403,
14669
+ * "prompt_tokens": 1340,
14543
14670
  * "cost": 0.0005595
14544
14671
  * }
14545
14672
  */
@@ -14603,7 +14730,7 @@ export interface OpenrouterRouterVideoEnterpriseInput {
14603
14730
  video_urls?: string[];
14604
14731
  }
14605
14732
 
14606
- export interface OpenrouterRouterVideoEnterpriseOutput extends SharedType_676 {}
14733
+ export interface OpenrouterRouterVideoEnterpriseOutput extends SharedType_cbb {}
14607
14734
 
14608
14735
  export interface OpenrouterRouterVideoInput {
14609
14736
  /**
@@ -14655,7 +14782,7 @@ export interface OpenrouterRouterVideoInput {
14655
14782
  video_urls?: string[];
14656
14783
  }
14657
14784
 
14658
- export interface OpenrouterRouterVideoOutput extends SharedType_676 {}
14785
+ export interface OpenrouterRouterVideoOutput extends SharedType_cbb {}
14659
14786
 
14660
14787
  export interface OpenrouterRouterAudioInput {
14661
14788
  /**
@@ -14714,9 +14841,9 @@ export interface OpenrouterRouterAudioOutput {
14714
14841
  /**
14715
14842
  * @description Token usage information
14716
14843
  * @example {
14717
- * "prompt_tokens": 500,
14718
- * "total_tokens": 550,
14719
14844
  * "completion_tokens": 50,
14845
+ * "total_tokens": 550,
14846
+ * "prompt_tokens": 500,
14720
14847
  * "cost": 0.0003
14721
14848
  * }
14722
14849
  */
@@ -14798,9 +14925,9 @@ export interface OpenrouterRouterOutput {
14798
14925
  /**
14799
14926
  * @description Token usage information
14800
14927
  * @example {
14801
- * "prompt_tokens": 40,
14802
- * "total_tokens": 267,
14803
14928
  * "completion_tokens": 227,
14929
+ * "total_tokens": 267,
14930
+ * "prompt_tokens": 40,
14804
14931
  * "cost": 0.0005795
14805
14932
  * }
14806
14933
  */
@@ -17594,13 +17721,6 @@ export interface WhisperInput {
17594
17721
  * @enum {string}
17595
17722
  */
17596
17723
  task?: 'transcribe' | 'translate';
17597
- /**
17598
- * Version
17599
- * @description Version of the model to use. All of the models are the Whisper large variant.
17600
- * @default 3
17601
- * @constant
17602
- */
17603
- version?: '3';
17604
17724
  }
17605
17725
 
17606
17726
  export interface WhisperOutput {
@@ -17722,6 +17842,7 @@ export interface WhisperOutput {
17722
17842
  /**
17723
17843
  * Text
17724
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.
17725
17846
  */
17726
17847
  text: string;
17727
17848
  }
@@ -25022,7 +25143,7 @@ export interface Swin2srInput {
25022
25143
  task?: 'classical_sr' | 'compressed_sr' | 'real_sr';
25023
25144
  }
25024
25145
 
25025
- export interface Swin2srOutput extends SharedType_e43 {}
25146
+ export interface Swin2srOutput extends SharedType_357 {}
25026
25147
 
25027
25148
  export interface StepxEdit2Input {
25028
25149
  /**
@@ -27882,54 +28003,67 @@ export interface SanaSprintOutput extends SharedType_7c6 {}
27882
28003
 
27883
28004
  export interface SanaVideoInput {
27884
28005
  /**
27885
- * Fps
27886
- * @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.
27887
28021
  * @default 16
27888
28022
  */
27889
- fps?: number;
28023
+ frames_per_second?: number;
27890
28024
  /**
27891
28025
  * Guidance Scale
27892
- * @description Guidance scale for generation (higher = more prompt adherence)
28026
+ * @description Guidance scale for generation (higher = more prompt adherence).
27893
28027
  * @default 6
27894
28028
  */
27895
28029
  guidance_scale?: number;
27896
28030
  /**
27897
28031
  * Motion Score
27898
- * @description Motion intensity score (higher = more motion)
28032
+ * @description Motion intensity score (higher = more motion).
27899
28033
  * @default 30
27900
28034
  */
27901
28035
  motion_score?: number;
27902
28036
  /**
27903
28037
  * Negative Prompt
27904
- * @description The negative prompt describing what to avoid in the generation
28038
+ * @description The negative prompt describing what to avoid in the generation.
27905
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.
27906
28040
  */
27907
28041
  negative_prompt?: string;
27908
28042
  /**
27909
28043
  * Num Frames
27910
- * @description Number of frames to generate
28044
+ * @description Number of frames to generate.
27911
28045
  * @default 81
27912
28046
  */
27913
28047
  num_frames?: number;
27914
28048
  /**
27915
28049
  * Num Inference Steps
27916
- * @description Number of denoising steps
28050
+ * @description Number of denoising steps.
27917
28051
  * @default 28
27918
28052
  */
27919
28053
  num_inference_steps?: number;
27920
28054
  /**
27921
28055
  * Prompt
27922
- * @description The text prompt describing the video to generate
28056
+ * @description The text prompt describing the video to generate.
27923
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.
27924
28058
  */
27925
28059
  prompt: string;
27926
28060
  /**
27927
28061
  * Resolution
27928
- * @description The resolution of the output video
28062
+ * @description The resolution of the output video.
27929
28063
  * @default 480p
27930
28064
  * @enum {string}
27931
28065
  */
27932
- resolution?: '480p';
28066
+ resolution?: '480p' | '720p';
27933
28067
  /**
27934
28068
  * Seed
27935
28069
  * @description Random seed for reproducible generation. If not provided, a random seed will be used.
@@ -27940,18 +28074,24 @@ export interface SanaVideoInput {
27940
28074
  export interface SanaVideoOutput {
27941
28075
  /**
27942
28076
  * Seed
27943
- * @description The random seed used for the generation process
28077
+ * @description The random seed used for the generation process.
27944
28078
  */
27945
28079
  seed: number;
27946
28080
  /**
27947
- * Video
27948
- * @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.
27949
28089
  * @example {
27950
28090
  * "content_type": "video/mp4",
27951
28091
  * "url": "https://v3b.fal.media/files/b/zebra/TipA9XXsXRYlB6vK6PQ0l_output.mp4"
27952
28092
  * }
27953
28093
  */
27954
- video: Components.File_1;
28094
+ video: Components.File;
27955
28095
  }
27956
28096
 
27957
28097
  export interface SanaInput extends SharedType_5f3 {}
@@ -27998,15 +28138,15 @@ export interface Sam2VideoInput {
27998
28138
  * @example [
27999
28139
  * {
28000
28140
  * "y": 350,
28001
- * "x": 210,
28141
+ * "label": 1,
28002
28142
  * "frame_index": 0,
28003
- * "label": 1
28143
+ * "x": 210
28004
28144
  * },
28005
28145
  * {
28006
28146
  * "y": 220,
28007
- * "x": 250,
28147
+ * "label": 1,
28008
28148
  * "frame_index": 0,
28009
- * "label": 1
28149
+ * "x": 250
28010
28150
  * }
28011
28151
  * ]
28012
28152
  */
@@ -28065,8 +28205,8 @@ export interface Sam2ImageInput {
28065
28205
  * @example [
28066
28206
  * {
28067
28207
  * "y": 375,
28068
- * "x": 500,
28069
- * "label": 1
28208
+ * "label": 1,
28209
+ * "x": 500
28070
28210
  * }
28071
28211
  * ]
28072
28212
  */
@@ -28870,7 +29010,7 @@ export interface Sa2va8bVideoOutput extends SharedType_800 {}
28870
29010
 
28871
29011
  export interface Sa2va8bImageInput extends SharedType_f51 {}
28872
29012
 
28873
- export interface Sa2va8bImageOutput extends SharedType_100 {}
29013
+ export interface Sa2va8bImageOutput extends SharedType_fda {}
28874
29014
 
28875
29015
  export interface Sa2va4bVideoInput extends SharedType_5f5 {}
28876
29016
 
@@ -28878,7 +29018,7 @@ export interface Sa2va4bVideoOutput extends SharedType_800 {}
28878
29018
 
28879
29019
  export interface Sa2va4bImageInput extends SharedType_f51 {}
28880
29020
 
28881
- export interface Sa2va4bImageOutput extends SharedType_100 {}
29021
+ export interface Sa2va4bImageOutput extends SharedType_fda {}
28882
29022
 
28883
29023
  export interface RifeVideoInput {
28884
29024
  /**
@@ -37275,13 +37415,13 @@ export interface NovaSrOutput {
37275
37415
  /**
37276
37416
  * @description The enhanced audio file.
37277
37417
  * @example {
37278
- * "bitrate": "192k",
37418
+ * "channels": 1,
37279
37419
  * "duration": 12.283291666666667,
37280
37420
  * "url": "https://v3b.fal.media/files/b/0a8a3f1a/lTKExJu-R6ZJdnFlpzEeq_TxmNTNhl.mp3",
37281
37421
  * "file_name": "lTKExJu-R6ZJdnFlpzEeq_TxmNTNhl.mp3",
37282
37422
  * "sample_rate": 48000,
37283
37423
  * "content_type": "audio/mpeg",
37284
- * "channels": 1
37424
+ * "bitrate": "192k"
37285
37425
  * }
37286
37426
  */
37287
37427
  audio: Components.AudioFile;
@@ -38147,7 +38287,6 @@ export interface MmaudioV2TextToAudioInput {
38147
38287
 
38148
38288
  export interface MmaudioV2TextToAudioOutput {
38149
38289
  /**
38150
- * Audio
38151
38290
  * @description The generated audio.
38152
38291
  * @example {
38153
38292
  * "file_size": 1001342,
@@ -38156,7 +38295,7 @@ export interface MmaudioV2TextToAudioOutput {
38156
38295
  * "url": "https://storage.googleapis.com/falserverless/model_tests/video_models/mmaudio_output.flac"
38157
38296
  * }
38158
38297
  */
38159
- audio: Components.File_1;
38298
+ audio: Components.File;
38160
38299
  }
38161
38300
 
38162
38301
  export interface MmaudioV2Input {
@@ -38211,7 +38350,6 @@ export interface MmaudioV2Input {
38211
38350
 
38212
38351
  export interface MmaudioV2Output {
38213
38352
  /**
38214
- * Video
38215
38353
  * @description The generated video with the lip sync.
38216
38354
  * @example {
38217
38355
  * "file_size": 1001342,
@@ -38220,7 +38358,7 @@ export interface MmaudioV2Output {
38220
38358
  * "url": "https://storage.googleapis.com/falserverless/model_tests/video_models/mmaudio_output.mp4"
38221
38359
  * }
38222
38360
  */
38223
- video: Components.File_1;
38361
+ video: Components.File;
38224
38362
  }
38225
38363
 
38226
38364
  export interface MixDehazeNetInput {
@@ -38243,7 +38381,13 @@ export interface MixDehazeNetInput {
38243
38381
  seed?: number;
38244
38382
  }
38245
38383
 
38246
- 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
+ }
38247
38391
 
38248
38392
  export interface MinimaxVoiceDesignInput {
38249
38393
  /**
@@ -40742,147 +40886,7 @@ export interface Ltxv13b098DistilledImageToVideoInput extends SharedType_2e6 {}
40742
40886
 
40743
40887
  export interface Ltxv13b098DistilledImageToVideoOutput extends SharedType_6711 {}
40744
40888
 
40745
- export interface Ltxv13b098DistilledExtendInput {
40746
- /**
40747
- * Aspect Ratio
40748
- * @description The aspect ratio of the video.
40749
- * @default auto
40750
- * @example auto
40751
- * @enum {string}
40752
- */
40753
- aspect_ratio?: '9:16' | '1:1' | '16:9' | 'auto';
40754
- /**
40755
- * Constant Rate Factor
40756
- * @description The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.
40757
- * @default 29
40758
- * @example 29
40759
- */
40760
- constant_rate_factor?: number;
40761
- /**
40762
- * Enable Detail Pass
40763
- * @description Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.
40764
- * @default false
40765
- * @example false
40766
- */
40767
- enable_detail_pass?: boolean;
40768
- /**
40769
- * Enable Safety Checker
40770
- * @description Whether to enable the safety checker.
40771
- * @default true
40772
- * @example true
40773
- */
40774
- enable_safety_checker?: boolean;
40775
- /**
40776
- * Expand Prompt
40777
- * @description Whether to expand the prompt using a language model.
40778
- * @default false
40779
- * @example false
40780
- */
40781
- expand_prompt?: boolean;
40782
- /**
40783
- * Number of Inference Steps
40784
- * @description Number of inference steps during the first pass.
40785
- * @default 8
40786
- * @example 8
40787
- */
40788
- first_pass_num_inference_steps?: number;
40789
- /**
40790
- * Frame Rate
40791
- * @description The frame rate of the video.
40792
- * @default 24
40793
- * @example 24
40794
- */
40795
- frame_rate?: number;
40796
- /**
40797
- * Loras
40798
- * @description LoRA weights to use for generation
40799
- * @default []
40800
- */
40801
- loras?: Components.LoRAWeight[];
40802
- /**
40803
- * Negative Prompt
40804
- * @description Negative prompt for generation
40805
- * @default worst quality, inconsistent motion, blurry, jittery, distorted
40806
- */
40807
- negative_prompt?: string;
40808
- /**
40809
- * Number of Frames
40810
- * @description The number of frames in the video.
40811
- * @default 121
40812
- * @example 121
40813
- */
40814
- num_frames?: number;
40815
- /**
40816
- * Prompt
40817
- * @description Text prompt to guide generation
40818
- * @example Woman walking on a street in Tokyo
40819
- */
40820
- prompt: string;
40821
- /**
40822
- * Resolution
40823
- * @description Resolution of the generated video.
40824
- * @default 720p
40825
- * @example 720p
40826
- * @enum {string}
40827
- */
40828
- resolution?: '480p' | '720p';
40829
- /**
40830
- * Reverse Video
40831
- * @description Whether to reverse the video.
40832
- * @default false
40833
- * @example false
40834
- */
40835
- reverse_video?: boolean;
40836
- /**
40837
- * Second Pass Number of Inference Steps
40838
- * @description Number of inference steps during the second pass.
40839
- * @default 8
40840
- * @example 8
40841
- */
40842
- second_pass_num_inference_steps?: number;
40843
- /**
40844
- * Second Pass Skip Initial Steps
40845
- * @description The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.
40846
- * @default 5
40847
- * @example 5
40848
- */
40849
- second_pass_skip_initial_steps?: number;
40850
- /**
40851
- * Seed
40852
- * @description Random seed for generation
40853
- */
40854
- seed?: number;
40855
- /**
40856
- * Temporal AdaIN Factor
40857
- * @description The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.
40858
- * @default 0.5
40859
- * @example 0.5
40860
- */
40861
- temporal_adain_factor?: number;
40862
- /**
40863
- * Tone Map Compression Ratio
40864
- * @description The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.
40865
- * @default 0
40866
- * @example 0
40867
- */
40868
- tone_map_compression_ratio?: number;
40869
- /**
40870
- * @description Video to be extended.
40871
- * @example {
40872
- * "video_url": "https://storage.googleapis.com/falserverless/web-examples/wan/t2v.mp4",
40873
- * "start_frame_num": 0,
40874
- * "reverse_video": false,
40875
- * "limit_num_frames": false,
40876
- * "resample_fps": false,
40877
- * "strength": 1,
40878
- * "target_fps": 24,
40879
- * "max_num_frames": 1441,
40880
- * "conditioning_type": "rgb",
40881
- * "preprocess": false
40882
- * }
40883
- */
40884
- video: Components.ExtendVideoConditioningInput;
40885
- }
40889
+ export interface Ltxv13b098DistilledExtendInput extends SharedType_133 {}
40886
40890
 
40887
40891
  export interface Ltxv13b098DistilledExtendOutput extends SharedType_844 {}
40888
40892
 
@@ -41068,165 +41072,13 @@ export interface Ltx2VideoTrainerInput {
41068
41072
  with_audio?: boolean;
41069
41073
  }
41070
41074
 
41071
- export interface Ltx2VideoTrainerOutput extends SharedType_f7a {}
41072
-
41073
- export interface Ltx2V2vTrainerInput {
41074
- /**
41075
- * Aspect Ratio
41076
- * @description Aspect ratio to use for training.
41077
- * @default 1:1
41078
- * @example 1:1
41079
- * @enum {string}
41080
- */
41081
- aspect_ratio?: '16:9' | '1:1' | '9:16';
41082
- /**
41083
- * Auto Scale Input
41084
- * @description If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.
41085
- * @default false
41086
- * @example false
41087
- */
41088
- auto_scale_input?: boolean;
41089
- /**
41090
- * Debug Dataset
41091
- * @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.
41092
- * @default false
41093
- */
41094
- debug_dataset?: boolean;
41095
- /**
41096
- * First Frame Conditioning P
41097
- * @description Probability of conditioning on the first frame during training. Lower values work better for video-to-video transformation.
41098
- * @default 0.1
41099
- */
41100
- first_frame_conditioning_p?: number;
41101
- /**
41102
- * Frame Rate
41103
- * @description Target frames per second for the video.
41104
- * @default 25
41105
- * @example 25
41106
- */
41107
- frame_rate?: number;
41108
- /**
41109
- * Learning Rate
41110
- * @description Learning rate for optimization. Higher values can lead to faster training but may cause overfitting.
41111
- * @default 0.0002
41112
- * @example 0.0002
41113
- */
41114
- learning_rate?: number;
41115
- /**
41116
- * Number Of Frames
41117
- * @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).
41118
- * @default 89
41119
- * @example 89
41120
- */
41121
- number_of_frames?: number;
41122
- /**
41123
- * Number Of Steps
41124
- * @description The number of training steps.
41125
- * @default 2000
41126
- * @example 2000
41127
- */
41128
- number_of_steps?: number;
41129
- /**
41130
- * Rank
41131
- * @description The rank of the LoRA adaptation. Higher values increase capacity but use more memory.
41132
- * @default 32
41133
- * @example 32
41134
- * @enum {integer}
41135
- */
41136
- rank?: 8 | 16 | 32 | 64 | 128;
41137
- /**
41138
- * Resolution
41139
- * @description Resolution to use for training. Higher resolutions require more memory.
41140
- * @default medium
41141
- * @example medium
41142
- * @enum {string}
41143
- */
41144
- resolution?: 'low' | 'medium' | 'high';
41145
- /**
41146
- * Split Input Duration Threshold
41147
- * @description The duration threshold in seconds. If a video is longer than this, it will be split into scenes.
41148
- * @default 30
41149
- * @example 30
41150
- */
41151
- split_input_duration_threshold?: number;
41152
- /**
41153
- * Split Input Into Scenes
41154
- * @description If true, videos above a certain duration threshold will be split into scenes.
41155
- * @default true
41156
- * @example true
41157
- */
41158
- split_input_into_scenes?: boolean;
41159
- /**
41160
- * Stg Scale
41161
- * @description STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0.
41162
- * @default 1
41163
- */
41164
- stg_scale?: number;
41165
- /**
41166
- * Training Data Url
41167
- * @description URL to zip archive with videos or images. Try to use at least 10 files, although more is better.
41168
- *
41169
- * **Supported video formats:** .mp4, .mov, .avi, .mkv
41170
- * **Supported image formats:** .png, .jpg, .jpeg
41171
- *
41172
- * Note: The dataset must contain ONLY videos OR ONLY images - mixed datasets are not supported.
41173
- *
41174
- * The archive can also contain text files with captions. Each text file should have the same name as the media file it corresponds to.
41175
- */
41176
- training_data_url: string;
41177
- /**
41178
- * Trigger Phrase
41179
- * @description A phrase that will trigger the LoRA style. Will be prepended to captions during training.
41180
- * @default
41181
- * @example
41182
- */
41183
- trigger_phrase?: string;
41184
- /**
41185
- * Validation
41186
- * @description A list of validation inputs with prompts and reference videos.
41187
- * @default []
41188
- */
41189
- validation?: Components.V2VValidation[];
41190
- /**
41191
- * Validation Aspect Ratio
41192
- * @description The aspect ratio to use for validation.
41193
- * @default 1:1
41194
- * @example 1:1
41195
- * @enum {string}
41196
- */
41197
- validation_aspect_ratio?: '16:9' | '1:1' | '9:16';
41198
- /**
41199
- * Validation Frame Rate
41200
- * @description Target frames per second for validation videos.
41201
- * @default 25
41202
- * @example 25
41203
- */
41204
- validation_frame_rate?: number;
41205
- /**
41206
- * Validation Negative Prompt
41207
- * @description A negative prompt to use for validation.
41208
- * @default worst quality, inconsistent motion, blurry, jittery, distorted
41209
- */
41210
- validation_negative_prompt?: string;
41211
- /**
41212
- * Validation Number Of Frames
41213
- * @description The number of frames in validation videos.
41214
- * @default 89
41215
- * @example 89
41216
- */
41217
- validation_number_of_frames?: number;
41218
- /**
41219
- * Validation Resolution
41220
- * @description The resolution to use for validation.
41221
- * @default high
41222
- * @example high
41223
- * @enum {string}
41224
- */
41225
- 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;
41226
41080
  }
41227
41081
 
41228
- export interface Ltx2V2vTrainerOutput extends SharedType_f7a {}
41229
-
41230
41082
  export interface LtxVideoImageToVideoInput {
41231
41083
  /**
41232
41084
  * Guidance Scale
@@ -41633,6 +41485,13 @@ export interface LtxVideoLoraMulticonditioningInput {
41633
41485
  * @enum {string}
41634
41486
  */
41635
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;
41636
41495
  /**
41637
41496
  * Enable Safety Checker
41638
41497
  * @description Whether to enable the safety checker.
@@ -41641,19 +41500,12 @@ export interface LtxVideoLoraMulticonditioningInput {
41641
41500
  */
41642
41501
  enable_safety_checker?: boolean;
41643
41502
  /**
41644
- * Expand Prompt
41645
- * @description Whether to expand the prompt using the LLM.
41646
- * @default false
41647
- * @example false
41648
- */
41649
- expand_prompt?: boolean;
41650
- /**
41651
- * Frame Rate
41503
+ * Frames Per Second
41652
41504
  * @description The frame rate of the video.
41653
41505
  * @default 25
41654
41506
  * @example 25
41655
41507
  */
41656
- frame_rate?: number;
41508
+ frames_per_second?: number;
41657
41509
  /**
41658
41510
  * Images
41659
41511
  * @description The image conditions to use for generation.
@@ -41684,6 +41536,13 @@ export interface LtxVideoLoraMulticonditioningInput {
41684
41536
  * @default blurry, low quality, low resolution, inconsistent motion, jittery, distorted
41685
41537
  */
41686
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;
41687
41546
  /**
41688
41547
  * Number Of Frames
41689
41548
  * @description The number of frames in the video.
@@ -41691,13 +41550,6 @@ export interface LtxVideoLoraMulticonditioningInput {
41691
41550
  * @example 89
41692
41551
  */
41693
41552
  number_of_frames?: number;
41694
- /**
41695
- * Number Of Steps
41696
- * @description The number of inference steps to use.
41697
- * @default 30
41698
- * @example 30
41699
- */
41700
- number_of_steps?: number;
41701
41553
  /**
41702
41554
  * Prompt
41703
41555
  * @description The prompt to generate the video from.
@@ -41762,6 +41614,13 @@ export interface LtxVideoLoraImageToVideoInput {
41762
41614
  * @enum {string}
41763
41615
  */
41764
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;
41765
41624
  /**
41766
41625
  * Enable Safety Checker
41767
41626
  * @description Whether to enable the safety checker.
@@ -41770,19 +41629,12 @@ export interface LtxVideoLoraImageToVideoInput {
41770
41629
  */
41771
41630
  enable_safety_checker?: boolean;
41772
41631
  /**
41773
- * Expand Prompt
41774
- * @description Whether to expand the prompt using the LLM.
41775
- * @default false
41776
- * @example false
41777
- */
41778
- expand_prompt?: boolean;
41779
- /**
41780
- * Frame Rate
41632
+ * Frames Per Second
41781
41633
  * @description The frame rate of the video.
41782
41634
  * @default 25
41783
41635
  * @example 25
41784
41636
  */
41785
- frame_rate?: number;
41637
+ frames_per_second?: number;
41786
41638
  /**
41787
41639
  * Image Url
41788
41640
  * @description The URL of the image to use as input.
@@ -41801,6 +41653,13 @@ export interface LtxVideoLoraImageToVideoInput {
41801
41653
  * @default blurry, low quality, low resolution, inconsistent motion, jittery, distorted
41802
41654
  */
41803
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;
41804
41663
  /**
41805
41664
  * Number Of Frames
41806
41665
  * @description The number of frames in the video.
@@ -41808,13 +41667,6 @@ export interface LtxVideoLoraImageToVideoInput {
41808
41667
  * @example 89
41809
41668
  */
41810
41669
  number_of_frames?: number;
41811
- /**
41812
- * Number Of Steps
41813
- * @description The number of inference steps to use.
41814
- * @default 30
41815
- * @example 30
41816
- */
41817
- number_of_steps?: number;
41818
41670
  /**
41819
41671
  * Prompt
41820
41672
  * @description The prompt to generate the video from.
@@ -41872,147 +41724,7 @@ export interface LtxVideo13bDistilledImageToVideoInput extends SharedType_2e6 {}
41872
41724
 
41873
41725
  export interface LtxVideo13bDistilledImageToVideoOutput extends SharedType_6711 {}
41874
41726
 
41875
- export interface LtxVideo13bDistilledExtendInput {
41876
- /**
41877
- * Aspect Ratio
41878
- * @description The aspect ratio of the video.
41879
- * @default auto
41880
- * @example auto
41881
- * @enum {string}
41882
- */
41883
- aspect_ratio?: '9:16' | '1:1' | '16:9' | 'auto';
41884
- /**
41885
- * Constant Rate Factor
41886
- * @description The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.
41887
- * @default 29
41888
- * @example 29
41889
- */
41890
- constant_rate_factor?: number;
41891
- /**
41892
- * Enable Detail Pass
41893
- * @description Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.
41894
- * @default false
41895
- * @example false
41896
- */
41897
- enable_detail_pass?: boolean;
41898
- /**
41899
- * Enable Safety Checker
41900
- * @description Whether to enable the safety checker.
41901
- * @default true
41902
- * @example true
41903
- */
41904
- enable_safety_checker?: boolean;
41905
- /**
41906
- * Expand Prompt
41907
- * @description Whether to expand the prompt using a language model.
41908
- * @default false
41909
- * @example false
41910
- */
41911
- expand_prompt?: boolean;
41912
- /**
41913
- * Number of Inference Steps
41914
- * @description Number of inference steps during the first pass.
41915
- * @default 8
41916
- * @example 8
41917
- */
41918
- first_pass_num_inference_steps?: number;
41919
- /**
41920
- * Frame Rate
41921
- * @description The frame rate of the video.
41922
- * @default 24
41923
- * @example 24
41924
- */
41925
- frame_rate?: number;
41926
- /**
41927
- * Loras
41928
- * @description LoRA weights to use for generation
41929
- * @default []
41930
- */
41931
- loras?: Components.LoRAWeight[];
41932
- /**
41933
- * Negative Prompt
41934
- * @description Negative prompt for generation
41935
- * @default worst quality, inconsistent motion, blurry, jittery, distorted
41936
- */
41937
- negative_prompt?: string;
41938
- /**
41939
- * Number of Frames
41940
- * @description The number of frames in the video.
41941
- * @default 121
41942
- * @example 121
41943
- */
41944
- num_frames?: number;
41945
- /**
41946
- * Prompt
41947
- * @description Text prompt to guide generation
41948
- * @example Woman walking on a street in Tokyo
41949
- */
41950
- prompt: string;
41951
- /**
41952
- * Resolution
41953
- * @description Resolution of the generated video.
41954
- * @default 720p
41955
- * @example 720p
41956
- * @enum {string}
41957
- */
41958
- resolution?: '480p' | '720p';
41959
- /**
41960
- * Reverse Video
41961
- * @description Whether to reverse the video.
41962
- * @default false
41963
- * @example false
41964
- */
41965
- reverse_video?: boolean;
41966
- /**
41967
- * Second Pass Number of Inference Steps
41968
- * @description Number of inference steps during the second pass.
41969
- * @default 8
41970
- * @example 8
41971
- */
41972
- second_pass_num_inference_steps?: number;
41973
- /**
41974
- * Second Pass Skip Initial Steps
41975
- * @description The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.
41976
- * @default 5
41977
- * @example 5
41978
- */
41979
- second_pass_skip_initial_steps?: number;
41980
- /**
41981
- * Seed
41982
- * @description Random seed for generation
41983
- */
41984
- seed?: number;
41985
- /**
41986
- * Temporal AdaIN Factor
41987
- * @description The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.
41988
- * @default 0.5
41989
- * @example 0.5
41990
- */
41991
- temporal_adain_factor?: number;
41992
- /**
41993
- * Tone Map Compression Ratio
41994
- * @description The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.
41995
- * @default 0
41996
- * @example 0
41997
- */
41998
- tone_map_compression_ratio?: number;
41999
- /**
42000
- * @description Video to be extended.
42001
- * @example {
42002
- * "video_url": "https://storage.googleapis.com/falserverless/web-examples/wan/t2v.mp4",
42003
- * "reverse_video": false,
42004
- * "start_frame_num": 0,
42005
- * "limit_num_frames": false,
42006
- * "resample_fps": false,
42007
- * "strength": 1,
42008
- * "target_fps": 24,
42009
- * "max_num_frames": 1441,
42010
- * "conditioning_type": "rgb",
42011
- * "preprocess": false
42012
- * }
42013
- */
42014
- video: Components.ExtendVideoConditioningInput;
42015
- }
41727
+ export interface LtxVideo13bDistilledExtendInput extends SharedType_133 {}
42016
41728
 
42017
41729
  export interface LtxVideo13bDistilledExtendOutput extends SharedType_844 {}
42018
41730
 
@@ -43490,7 +43202,7 @@ export interface Ltx219bVideoToVideoLoraInput {
43490
43202
  video_write_mode?: 'fast' | 'balanced' | 'small';
43491
43203
  }
43492
43204
 
43493
- export interface Ltx219bVideoToVideoLoraOutput extends SharedType_3b0 {}
43205
+ export interface Ltx219bVideoToVideoLoraOutput extends SharedType_1f5 {}
43494
43206
 
43495
43207
  export interface Ltx219bVideoToVideoInput {
43496
43208
  /**
@@ -43712,7 +43424,7 @@ export interface Ltx219bVideoToVideoInput {
43712
43424
  video_write_mode?: 'fast' | 'balanced' | 'small';
43713
43425
  }
43714
43426
 
43715
- export interface Ltx219bVideoToVideoOutput extends SharedType_3b0 {}
43427
+ export interface Ltx219bVideoToVideoOutput extends SharedType_1f5 {}
43716
43428
 
43717
43429
  export interface Ltx219bTextToVideoLoraInput {
43718
43430
  /**
@@ -43859,7 +43571,7 @@ export interface Ltx219bTextToVideoLoraInput {
43859
43571
  video_write_mode?: 'fast' | 'balanced' | 'small';
43860
43572
  }
43861
43573
 
43862
- export interface Ltx219bTextToVideoLoraOutput extends SharedType_857 {}
43574
+ export interface Ltx219bTextToVideoLoraOutput extends SharedType_6ef {}
43863
43575
 
43864
43576
  export interface Ltx219bTextToVideoInput {
43865
43577
  /**
@@ -44001,7 +43713,7 @@ export interface Ltx219bTextToVideoInput {
44001
43713
  video_write_mode?: 'fast' | 'balanced' | 'small';
44002
43714
  }
44003
43715
 
44004
- export interface Ltx219bTextToVideoOutput extends SharedType_857 {}
43716
+ export interface Ltx219bTextToVideoOutput extends SharedType_6ef {}
44005
43717
 
44006
43718
  export interface Ltx219bImageToVideoLoraInput {
44007
43719
  /**
@@ -44179,7 +43891,7 @@ export interface Ltx219bImageToVideoLoraInput {
44179
43891
  video_write_mode?: 'fast' | 'balanced' | 'small';
44180
43892
  }
44181
43893
 
44182
- export interface Ltx219bImageToVideoLoraOutput extends SharedType_369 {}
43894
+ export interface Ltx219bImageToVideoLoraOutput extends SharedType_437 {}
44183
43895
 
44184
43896
  export interface Ltx219bImageToVideoInput {
44185
43897
  /**
@@ -44352,7 +44064,7 @@ export interface Ltx219bImageToVideoInput {
44352
44064
  video_write_mode?: 'fast' | 'balanced' | 'small';
44353
44065
  }
44354
44066
 
44355
- export interface Ltx219bImageToVideoOutput extends SharedType_369 {}
44067
+ export interface Ltx219bImageToVideoOutput extends SharedType_437 {}
44356
44068
 
44357
44069
  export interface Ltx219bExtendVideoLoraInput {
44358
44070
  /**
@@ -44548,7 +44260,7 @@ export interface Ltx219bExtendVideoLoraInput {
44548
44260
  video_write_mode?: 'fast' | 'balanced' | 'small';
44549
44261
  }
44550
44262
 
44551
- export interface Ltx219bExtendVideoLoraOutput extends SharedType_cb6 {}
44263
+ export interface Ltx219bExtendVideoLoraOutput extends SharedType_5db {}
44552
44264
 
44553
44265
  export interface Ltx219bExtendVideoInput {
44554
44266
  /**
@@ -44739,7 +44451,7 @@ export interface Ltx219bExtendVideoInput {
44739
44451
  video_write_mode?: 'fast' | 'balanced' | 'small';
44740
44452
  }
44741
44453
 
44742
- export interface Ltx219bExtendVideoOutput extends SharedType_cb6 {}
44454
+ export interface Ltx219bExtendVideoOutput extends SharedType_5db {}
44743
44455
 
44744
44456
  export interface Ltx219bDistilledVideoToVideoLoraInput {
44745
44457
  /**
@@ -44954,7 +44666,7 @@ export interface Ltx219bDistilledVideoToVideoLoraInput {
44954
44666
  video_write_mode?: 'fast' | 'balanced' | 'small';
44955
44667
  }
44956
44668
 
44957
- export interface Ltx219bDistilledVideoToVideoLoraOutput extends SharedType_3b0 {}
44669
+ export interface Ltx219bDistilledVideoToVideoLoraOutput extends SharedType_1f5 {}
44958
44670
 
44959
44671
  export interface Ltx219bDistilledVideoToVideoInput {
44960
44672
  /**
@@ -45164,7 +44876,7 @@ export interface Ltx219bDistilledVideoToVideoInput {
45164
44876
  video_write_mode?: 'fast' | 'balanced' | 'small';
45165
44877
  }
45166
44878
 
45167
- export interface Ltx219bDistilledVideoToVideoOutput extends SharedType_3b0 {}
44879
+ export interface Ltx219bDistilledVideoToVideoOutput extends SharedType_1f5 {}
45168
44880
 
45169
44881
  export interface Ltx219bDistilledTextToVideoLoraInput {
45170
44882
  /**
@@ -45299,7 +45011,7 @@ export interface Ltx219bDistilledTextToVideoLoraInput {
45299
45011
  video_write_mode?: 'fast' | 'balanced' | 'small';
45300
45012
  }
45301
45013
 
45302
- export interface Ltx219bDistilledTextToVideoLoraOutput extends SharedType_857 {}
45014
+ export interface Ltx219bDistilledTextToVideoLoraOutput extends SharedType_6ef {}
45303
45015
 
45304
45016
  export interface Ltx219bDistilledTextToVideoInput {
45305
45017
  /**
@@ -45429,7 +45141,7 @@ export interface Ltx219bDistilledTextToVideoInput {
45429
45141
  video_write_mode?: 'fast' | 'balanced' | 'small';
45430
45142
  }
45431
45143
 
45432
- export interface Ltx219bDistilledTextToVideoOutput extends SharedType_857 {}
45144
+ export interface Ltx219bDistilledTextToVideoOutput extends SharedType_6ef {}
45433
45145
 
45434
45146
  export interface Ltx219bDistilledImageToVideoLoraInput {
45435
45147
  /**
@@ -45595,7 +45307,7 @@ export interface Ltx219bDistilledImageToVideoLoraInput {
45595
45307
  video_write_mode?: 'fast' | 'balanced' | 'small';
45596
45308
  }
45597
45309
 
45598
- export interface Ltx219bDistilledImageToVideoLoraOutput extends SharedType_369 {}
45310
+ export interface Ltx219bDistilledImageToVideoLoraOutput extends SharedType_437 {}
45599
45311
 
45600
45312
  export interface Ltx219bDistilledImageToVideoInput {
45601
45313
  /**
@@ -45756,7 +45468,7 @@ export interface Ltx219bDistilledImageToVideoInput {
45756
45468
  video_write_mode?: 'fast' | 'balanced' | 'small';
45757
45469
  }
45758
45470
 
45759
- export interface Ltx219bDistilledImageToVideoOutput extends SharedType_369 {}
45471
+ export interface Ltx219bDistilledImageToVideoOutput extends SharedType_437 {}
45760
45472
 
45761
45473
  export interface Ltx219bDistilledExtendVideoLoraInput {
45762
45474
  /**
@@ -45940,7 +45652,7 @@ export interface Ltx219bDistilledExtendVideoLoraInput {
45940
45652
  video_write_mode?: 'fast' | 'balanced' | 'small';
45941
45653
  }
45942
45654
 
45943
- export interface Ltx219bDistilledExtendVideoLoraOutput extends SharedType_cb6 {}
45655
+ export interface Ltx219bDistilledExtendVideoLoraOutput extends SharedType_5db {}
45944
45656
 
45945
45657
  export interface Ltx219bDistilledExtendVideoInput {
45946
45658
  /**
@@ -46119,7 +45831,7 @@ export interface Ltx219bDistilledExtendVideoInput {
46119
45831
  video_write_mode?: 'fast' | 'balanced' | 'small';
46120
45832
  }
46121
45833
 
46122
- export interface Ltx219bDistilledExtendVideoOutput extends SharedType_cb6 {}
45834
+ export interface Ltx219bDistilledExtendVideoOutput extends SharedType_5db {}
46123
45835
 
46124
45836
  export interface Ltx219bDistilledAudioToVideoLoraInput {
46125
45837
  /**
@@ -49324,9 +49036,9 @@ export interface LightxRelightInput {
49324
49036
  /**
49325
49037
  * @description Relighting parameters (required for relight_condition_type='ic'). Not used for 'bg' (which expects a background image URL instead).
49326
49038
  * @example {
49327
- * "use_sky_mask": false,
49328
- * "bg_source": "Right",
49329
49039
  * "relight_prompt": "Sunlight",
49040
+ * "bg_source": "Right",
49041
+ * "use_sky_mask": false,
49330
49042
  * "cfg": 2
49331
49043
  * }
49332
49044
  */
@@ -58548,17 +58260,17 @@ export interface Hunyuan3dV3TextTo3dOutput {
58548
58260
  /**
58549
58261
  * @description URLs for different 3D model formats
58550
58262
  * @example {
58551
- * "obj": {
58552
- * "file_size": 44084728,
58553
- * "file_name": "model.obj",
58554
- * "content_type": "text/plain",
58555
- * "url": "https://v3b.fal.media/files/b/0a8686a8/AVgdsVFrGAKGAFr4e2g56_model.obj"
58556
- * },
58557
58263
  * "glb": {
58558
58264
  * "file_size": 64724836,
58559
58265
  * "file_name": "model.glb",
58560
58266
  * "content_type": "model/gltf-binary",
58561
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"
58562
58274
  * }
58563
58275
  * }
58564
58276
  */
@@ -58717,17 +58429,17 @@ export interface Hunyuan3dV3ImageTo3dOutput {
58717
58429
  /**
58718
58430
  * @description URLs for different 3D model formats
58719
58431
  * @example {
58720
- * "obj": {
58721
- * "file_size": 42886419,
58722
- * "file_name": "model.obj",
58723
- * "content_type": "text/plain",
58724
- * "url": "https://v3b.fal.media/files/b/0a8686ad/ifdJskhUfQysq-NN20iQR_model.obj"
58725
- * },
58726
58432
  * "glb": {
58727
58433
  * "file_size": 64122888,
58728
58434
  * "file_name": "model.glb",
58729
58435
  * "content_type": "model/gltf-binary",
58730
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"
58731
58443
  * }
58732
58444
  * }
58733
58445
  */
@@ -60483,8 +60195,8 @@ export interface Hunyuan_worldOutput {
60483
60195
  /**
60484
60196
  * @description The generated panorama image.
60485
60197
  * @example {
60486
- * "file_size": 2738127,
60487
60198
  * "height": 960,
60199
+ * "file_size": 2738127,
60488
60200
  * "file_name": "5db7925423b44f2a98098cd8f7cad7ec.png",
60489
60201
  * "content_type": "image/png",
60490
60202
  * "url": "https://v3.fal.media/files/kangaroo/P2AmXuLlyDIsivqjV_rAr_5db7925423b44f2a98098cd8f7cad7ec.png",
@@ -62410,9 +62122,9 @@ export interface FooocusUpscaleOrVaryInput {
62410
62122
  * Styles
62411
62123
  * @description The style to use.
62412
62124
  * @default [
62413
- * "Fooocus Enhance",
62414
62125
  * "Fooocus V2",
62415
- * "Fooocus Sharp"
62126
+ * "Fooocus Sharp",
62127
+ * "Fooocus Enhance"
62416
62128
  * ]
62417
62129
  */
62418
62130
  styles?: (
@@ -62919,9 +62631,9 @@ export interface FooocusInpaintInput {
62919
62631
  * Styles
62920
62632
  * @description The style to use.
62921
62633
  * @default [
62922
- * "Fooocus Enhance",
62923
62634
  * "Fooocus V2",
62924
- * "Fooocus Sharp"
62635
+ * "Fooocus Sharp",
62636
+ * "Fooocus Enhance"
62925
62637
  * ]
62926
62638
  */
62927
62639
  styles?: (
@@ -63236,10 +62948,10 @@ export interface FooocusImagePromptInput {
63236
62948
  guidance_scale?: number;
63237
62949
  /**
63238
62950
  * @example {
63239
- * "image_url": "https://storage.googleapis.com/falserverless/model_tests/fooocus/Pikachu.webp",
62951
+ * "weight": 1,
63240
62952
  * "stop_at": 1,
63241
62953
  * "type": "PyraCanny",
63242
- * "weight": 1
62954
+ * "image_url": "https://storage.googleapis.com/falserverless/model_tests/fooocus/Pikachu.webp"
63243
62955
  * }
63244
62956
  */
63245
62957
  image_prompt_1: Components.ImagePrompt;
@@ -63370,9 +63082,9 @@ export interface FooocusImagePromptInput {
63370
63082
  * Styles
63371
63083
  * @description The style to use.
63372
63084
  * @default [
63373
- * "Fooocus Enhance",
63374
63085
  * "Fooocus V2",
63375
- * "Fooocus Sharp"
63086
+ * "Fooocus Sharp",
63087
+ * "Fooocus Enhance"
63376
63088
  * ]
63377
63089
  */
63378
63090
  styles?: (
@@ -63828,9 +63540,9 @@ export interface FooocusInput {
63828
63540
  * Styles
63829
63541
  * @description The style to use.
63830
63542
  * @default [
63831
- * "Fooocus Enhance",
63832
63543
  * "Fooocus V2",
63833
- * "Fooocus Sharp"
63544
+ * "Fooocus Sharp",
63545
+ * "Fooocus Enhance"
63834
63546
  * ]
63835
63547
  */
63836
63548
  styles?: (
@@ -64790,8 +64502,8 @@ export interface FluxVisionUpscalerOutput {
64790
64502
  /**
64791
64503
  * @description The URL of the generated image.
64792
64504
  * @example {
64793
- * "file_size": 8842156,
64794
64505
  * "height": 2048,
64506
+ * "file_size": 8842156,
64795
64507
  * "file_name": "20TZeUQtQ8oKgsCKXSL81_StableSR_00002_.png",
64796
64508
  * "content_type": "image/png",
64797
64509
  * "url": "https://v3b.fal.media/files/b/panda/20TZeUQtQ8oKgsCKXSL81_StableSR_00002_.png",
@@ -71795,15 +71507,15 @@ export interface FloweditOutput {
71795
71507
  seed: number;
71796
71508
  }
71797
71509
 
71798
- export interface Florence2LargeRegionToSegmentationInput extends SharedType_2ff {}
71510
+ export interface Florence2LargeRegionToSegmentationInput extends SharedType_8b7 {}
71799
71511
 
71800
71512
  export interface Florence2LargeRegionToSegmentationOutput extends SharedType_4aa {}
71801
71513
 
71802
- export interface Florence2LargeRegionToDescriptionInput extends SharedType_2ff {}
71514
+ export interface Florence2LargeRegionToDescriptionInput extends SharedType_8b7 {}
71803
71515
 
71804
71516
  export interface Florence2LargeRegionToDescriptionOutput extends SharedType_129 {}
71805
71517
 
71806
- export interface Florence2LargeRegionToCategoryInput extends SharedType_2ff {}
71518
+ export interface Florence2LargeRegionToCategoryInput extends SharedType_8b7 {}
71807
71519
 
71808
71520
  export interface Florence2LargeRegionToCategoryOutput extends SharedType_129 {}
71809
71521
 
@@ -77347,51 +77059,6 @@ export interface Deepfilternet3Output {
77347
77059
  timings: Components.DeepFilterNetTimings;
77348
77060
  }
77349
77061
 
77350
- export interface DecartLucy5bImageToVideoInput {
77351
- /**
77352
- * Aspect Ratio
77353
- * @description Aspect ratio of the generated video.
77354
- * @default 16:9
77355
- * @enum {string}
77356
- */
77357
- aspect_ratio?: '9:16' | '16:9';
77358
- /**
77359
- * Image Url
77360
- * @description URL of the image to use as the first frame
77361
- * @example https://v3.fal.media/files/monkey/OlpQEYh7oNeJ3qKsdiaym_ia5ECOgFbfcniMDu01_18_da73e078e0924472b51d92f3e3fba98c.png
77362
- */
77363
- image_url: string;
77364
- /**
77365
- * Prompt
77366
- * @description Text description of the desired video content
77367
- * @example A cat is walking slowly in the garden
77368
- */
77369
- prompt: string;
77370
- /**
77371
- * Resolution
77372
- * @description Resolution of the generated video
77373
- * @default 720p
77374
- * @constant
77375
- */
77376
- resolution?: '720p';
77377
- /**
77378
- * Sync Mode
77379
- * @description If `True`, the media will be returned as a data URI and the output data won't be available in the request history.
77380
- * @default true
77381
- */
77382
- sync_mode?: boolean;
77383
- }
77384
-
77385
- export interface DecartLucy5bImageToVideoOutput {
77386
- /**
77387
- * @description The generated MP4 video with H.264 encoding
77388
- * @example {
77389
- * "url": "https://v3.fal.media/files/kangaroo/rIFaCsyWvBxYBKw3cPbOU_indir.mp4"
77390
- * }
77391
- */
77392
- video: Components.File;
77393
- }
77394
-
77395
77062
  export interface DdcolorInput {
77396
77063
  /**
77397
77064
  * Image Url
@@ -78191,7 +77858,7 @@ export interface Cogvideox5bVideoToVideoInput {
78191
77858
  video_url: string;
78192
77859
  }
78193
77860
 
78194
- export interface Cogvideox5bVideoToVideoOutput extends SharedType_1001 {}
77861
+ export interface Cogvideox5bVideoToVideoOutput extends SharedType_100 {}
78195
77862
 
78196
77863
  export interface Cogvideox5bImageToVideoInput {
78197
77864
  /**
@@ -78270,7 +77937,7 @@ export interface Cogvideox5bImageToVideoInput {
78270
77937
  );
78271
77938
  }
78272
77939
 
78273
- export interface Cogvideox5bImageToVideoOutput extends SharedType_1001 {}
77940
+ export interface Cogvideox5bImageToVideoOutput extends SharedType_100 {}
78274
77941
 
78275
77942
  export interface Cogvideox5bInput {
78276
77943
  /**
@@ -78343,7 +78010,7 @@ export interface Cogvideox5bInput {
78343
78010
  );
78344
78011
  }
78345
78012
 
78346
- export interface Cogvideox5bOutput extends SharedType_1001 {}
78013
+ export interface Cogvideox5bOutput extends SharedType_100 {}
78347
78014
 
78348
78015
  export interface CodeformerInput {
78349
78016
  /**
@@ -78393,8 +78060,8 @@ export interface CodeformerOutput {
78393
78060
  /**
78394
78061
  * @description The generated image file info.
78395
78062
  * @example {
78396
- * "height": 512,
78397
78063
  * "file_size": 423052,
78064
+ * "height": 512,
78398
78065
  * "file_name": "36d3ca4791a647678b2ff01a35c87f5a.png",
78399
78066
  * "content_type": "image/png",
78400
78067
  * "url": "https://storage.googleapis.com/falserverless/model_tests/codeformer/codeformer_restored_1.jpeg",
@@ -79250,95 +78917,6 @@ export interface CartoonifyInput {
79250
78917
 
79251
78918
  export interface CartoonifyOutput extends SharedType_7c6 {}
79252
78919
 
79253
- export interface CalligrapherInput {
79254
- /**
79255
- * Auto Mask Generation
79256
- * @description Whether to automatically generate mask from detected text
79257
- * @default false
79258
- */
79259
- auto_mask_generation?: boolean;
79260
- /**
79261
- * Cfg Scale
79262
- * @description Guidance or strength scale for the model
79263
- * @default 1
79264
- */
79265
- cfg_scale?: number;
79266
- /**
79267
- * Image Size
79268
- * @description Target image size for generation
79269
- * @default {
79270
- * "height": 1024,
79271
- * "width": 1024
79272
- * }
79273
- */
79274
- image_size?:
79275
- | Components.ImageSize
79276
- | (
79277
- | 'square_hd'
79278
- | 'square'
79279
- | 'portrait_4_3'
79280
- | 'portrait_16_9'
79281
- | 'landscape_4_3'
79282
- | 'landscape_16_9'
79283
- );
79284
- /**
79285
- * Mask Image Url
79286
- * @description Base64-encoded mask image (optional if using auto_mask_generation)
79287
- * @example https://storage.googleapis.com/falserverless/calligrapher/test17_mask.png
79288
- */
79289
- mask_image_url?: string;
79290
- /**
79291
- * Num Images
79292
- * @description How many images to generate
79293
- * @default 1
79294
- */
79295
- num_images?: number;
79296
- /**
79297
- * Num Inference Steps
79298
- * @description Number of inference steps (1-100)
79299
- * @default 50
79300
- */
79301
- num_inference_steps?: number;
79302
- /**
79303
- * Prompt
79304
- * @description Text prompt to inpaint or customize
79305
- * @example The text is 'Rise'
79306
- */
79307
- prompt: string;
79308
- /**
79309
- * Reference Image Url
79310
- * @description Optional base64 reference image for style
79311
- */
79312
- reference_image_url?: string;
79313
- /**
79314
- * Seed
79315
- * @description Random seed for reproducibility
79316
- */
79317
- seed?: number;
79318
- /**
79319
- * Source Image Url
79320
- * @description Base64-encoded source image with drawn mask layers
79321
- * @example https://storage.googleapis.com/falserverless/calligrapher/test17_source.png
79322
- */
79323
- source_image_url: string;
79324
- /**
79325
- * Source Text
79326
- * @description Source text to replace (if empty, masks all detected text)
79327
- * @default
79328
- */
79329
- source_text?: string;
79330
- /**
79331
- * Use Context
79332
- * @description Whether to prepend context reference to the input
79333
- * @default true
79334
- */
79335
- use_context?: boolean;
79336
- }
79337
-
79338
- export interface CalligrapherOutput {
79339
- images: Components.Image[];
79340
- }
79341
-
79342
78920
  export interface BytedanceVideoStylizeInput {
79343
78921
  /**
79344
78922
  * Image Url
@@ -80870,7 +80448,7 @@ export interface BytedanceUpscalerUpscaleVideoOutput {
80870
80448
 
80871
80449
  export interface BriaTextToImageHdInput extends SharedType_411 {}
80872
80450
 
80873
- export interface BriaTextToImageHdOutput extends SharedType_a97 {}
80451
+ export interface BriaTextToImageHdOutput extends SharedType_e19 {}
80874
80452
 
80875
80453
  export interface BriaTextToImageFastInput {
80876
80454
  /**
@@ -80943,11 +80521,11 @@ export interface BriaTextToImageFastInput {
80943
80521
  sync_mode?: boolean;
80944
80522
  }
80945
80523
 
80946
- export interface BriaTextToImageFastOutput extends SharedType_a97 {}
80524
+ export interface BriaTextToImageFastOutput extends SharedType_e19 {}
80947
80525
 
80948
80526
  export interface BriaTextToImageBaseInput extends SharedType_411 {}
80949
80527
 
80950
- export interface BriaTextToImageBaseOutput extends SharedType_a97 {}
80528
+ export interface BriaTextToImageBaseOutput extends SharedType_e19 {}
80951
80529
 
80952
80530
  export interface BriaReimagineInput {
80953
80531
  /**
@@ -81176,8 +80754,8 @@ export interface BriaGenfillOutput {
81176
80754
  * @description Generated Images
81177
80755
  * @example [
81178
80756
  * {
81179
- * "file_size": 1064550,
81180
80757
  * "height": 768,
80758
+ * "file_size": 1064550,
81181
80759
  * "file_name": "a0d138e6820c4ad58f1fd3c758f16047.png",
81182
80760
  * "content_type": "image/png",
81183
80761
  * "url": "https://storage.googleapis.com/falserverless/bria/bria_genfill_res.png",
@@ -81261,8 +80839,8 @@ export interface BriaExpandOutput {
81261
80839
  /**
81262
80840
  * @description The generated image
81263
80841
  * @example {
81264
- * "file_size": 1471342,
81265
80842
  * "height": 674,
80843
+ * "file_size": 1471342,
81266
80844
  * "file_name": "afa402a35ea742cdb5c3e219b2b19bfb.png",
81267
80845
  * "content_type": "image/png",
81268
80846
  * "url": "https://v3.fal.media/files/koala/8np-spgxxG-I1r3cjthRV_afa402a35ea742cdb5c3e219b2b19bfb.png",
@@ -81418,8 +80996,8 @@ export interface BriaBackgroundRemoveOutput {
81418
80996
  /**
81419
80997
  * @description The generated image
81420
80998
  * @example {
81421
- * "file_size": 1076276,
81422
80999
  * "height": 1024,
81000
+ * "file_size": 1076276,
81423
81001
  * "file_name": "070c731993e949d993c10ef6283d335d.png",
81424
81002
  * "content_type": "image/png",
81425
81003
  * "url": "https://v3.fal.media/files/tiger/GQEMNjRyxSoza7N8LPPqb_070c731993e949d993c10ef6283d335d.png",
@@ -81618,8 +81196,8 @@ export interface BirefnetV2VideoOutput {
81618
81196
  * "height": 1080,
81619
81197
  * "duration": 8,
81620
81198
  * "url": "https://storage.googleapis.com/falserverless/example_outputs/birefnet-video-output.webm",
81621
- * "width": 1920,
81622
81199
  * "fps": 24,
81200
+ * "width": 1920,
81623
81201
  * "file_name": "birefnet-video-output.webm",
81624
81202
  * "num_frames": 192,
81625
81203
  * "content_type": "video/webm"
@@ -81915,8 +81493,8 @@ export interface BagelEditOutput {
81915
81493
  * @description The edited images.
81916
81494
  * @example [
81917
81495
  * {
81918
- * "height": 1024,
81919
81496
  * "file_size": 423052,
81497
+ * "height": 1024,
81920
81498
  * "file_name": "hQnndOMvGSt2UsYAiV3vs.jpeg",
81921
81499
  * "content_type": "image/jpeg",
81922
81500
  * "url": "https://storage.googleapis.com/falserverless/bagel/hQnndOMvGSt2UsYAiV3vs.jpeg",
@@ -81978,8 +81556,8 @@ export interface BagelOutput {
81978
81556
  * @description The generated images.
81979
81557
  * @example [
81980
81558
  * {
81981
- * "height": 1024,
81982
81559
  * "file_size": 423052,
81560
+ * "height": 1024,
81983
81561
  * "file_name": "wRhCPSyiKTiLnnWvUpGIl.jpeg",
81984
81562
  * "content_type": "image/jpeg",
81985
81563
  * "url": "https://storage.googleapis.com/falserverless/bagel/wRhCPSyiKTiLnnWvUpGIl.jpeg",
@@ -83582,11 +83160,11 @@ export interface ClarityaiCrystalVideoUpscalerOutput {
83582
83160
  * "height": 2160,
83583
83161
  * "duration": 13.056527,
83584
83162
  * "url": "https://storage.googleapis.com/falserverless/example_outputs/crystal_upscaler/video_upscaling/video_out.mp4",
83585
- * "fps": 23.130193905817176,
83586
83163
  * "width": 4096,
83164
+ * "fps": 23.130193905817176,
83587
83165
  * "file_name": "w0VQQvPdwvV2GSCtRTMzh_hDH8SPrB.mp4",
83588
- * "content_type": "video/mp4",
83589
- * "num_frames": 302
83166
+ * "num_frames": 302,
83167
+ * "content_type": "video/mp4"
83590
83168
  * }
83591
83169
  */
83592
83170
  video: Components.VideoFile;