fal-endpoint-types 1.3.24 → 1.3.26

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "fal-endpoint-types",
-    "version": "1.3.24",
+    "version": "1.3.26",
     "description": "TypeScript types for Fal AI endpoints generated from the OpenAPI schemas.",
     "homepage": "https://github.com/rawpixel-vincent/fal-endpoint-types#readme",
     "bugs": {

package/types/fal/endpoints/components.d.ts

@@ -26,14 +26,18 @@ export interface WhisperChunk {
      * Timestamp
      * @description Start and end timestamp of the chunk
      */
-    timestamp: { [x: string]: any }[];
+    timestamp: [number, number];
 }
 
 export interface VoiceSetting {
+    /**
+     * Custom Voice Id
+     * @description Custom cloned voice ID. If provided, this will override the voice_id field.
+     */
+    custom_voice_id?: string;
     /**
      * Emotion
      * @description Emotion of the generated speech
-     * @enum {string}
      */
     emotion?: 'happy' | 'sad' | 'angry' | 'fearful' | 'disgusted' | 'surprised' | 'neutral';
     /**
@@ -247,7 +251,7 @@ export interface VideoFile {
     width?: number;
 }
 
-export interface VideoConditioningInput_2 {
+export interface VideoConditioningInput_3 {
     /**
      * Conditioning Type
      * @description Type of conditioning this video provides. This is relevant to ensure in-context LoRA weights are applied correctly, as well as selecting the correct preprocessing pipeline, when enabled.
@@ -313,7 +317,7 @@ export interface VideoConditioningInput_2 {
     video_url: string;
 }
 
-export interface VideoConditioningInput_1 {
+export interface VideoConditioningInput_2 {
     /**
      * Start Frame Num
      * @description Frame number of the video from which the conditioning starts. Must be a multiple of 8.
@@ -326,7 +330,7 @@ export interface VideoConditioningInput_1 {
     video_url: string;
 }
 
-export interface VideoConditioningInput {
+export interface VideoConditioningInput_1 {
     /**
      * Conditioning Type
      * @description Type of conditioning this video provides. This is relevant to ensure in-context LoRA weights are applied correctly, as well as selecting the correct preprocessing pipeline, when enabled.
@@ -392,6 +396,71 @@ export interface VideoConditioningInput {
     video_url: string;
 }
 
+export interface VideoConditioningInput {
+    /**
+     * Conditioning Type
+     * @description Type of conditioning this video provides. This is relevant to ensure in-context LoRA weights are applied correctly, as well as selecting the correct preprocessing pipeline, when enabled.
+     * @default rgb
+     * @example rgb
+     */
+    conditioning_type?: 'rgb' | 'depth' | 'pose' | 'canny';
+    /**
+     * Limit Number of Frames
+     * @description Whether to limit the number of frames used from the video. If True, the `max_num_frames` parameter will be used to limit the number of frames.
+     * @default false
+     */
+    limit_num_frames?: boolean;
+    /**
+     * Maximum Number of Frames
+     * @description Maximum number of frames to use from the video. If None, all frames will be used.
+     * @default 1441
+     * @example 1441
+     */
+    max_num_frames?: number;
+    /**
+     * Preprocess
+     * @description Whether to preprocess the video. If True, the video will be preprocessed to match the conditioning type. This is a no-op for RGB conditioning.
+     * @default false
+     */
+    preprocess?: boolean;
+    /**
+     * Resample FPS
+     * @description Whether to resample the video to a specific FPS. If True, the `target_fps` parameter will be used to resample the video.
+     * @default false
+     */
+    resample_fps?: boolean;
+    /**
+     * Reverse Video
+     * @description Whether to reverse the video. This is useful for tasks where the video conditioning should be applied in reverse order.
+     * @default false
+     */
+    reverse_video?: boolean;
+    /**
+     * Start Frame Number
+     * @description Frame number of the video from which the conditioning starts. Must be a multiple of 8.
+     * @default 0
+     */
+    start_frame_num?: number;
+    /**
+     * Strength
+     * @description Strength of the conditioning. 0.0 means no conditioning, 1.0 means full conditioning.
+     * @default 1
+     */
+    strength?: number;
+    /**
+     * Target FPS
+     * @description Target FPS to resample the video to. Only relevant if `resample_fps` is True.
+     * @default 24
+     * @example 24
+     */
+    target_fps?: number;
+    /**
+     * Video URL
+     * @description URL of video to use as conditioning
+     */
+    video_url: string;
+}
+
 export interface VideoCondition {
     /**
      * Start Frame Number
@@ -761,22 +830,22 @@ export interface TextureFiles {
      * Base Color
      * @description Base color texture
      */
-    base_color: File_1;
+    base_color: File;
     /**
      * Metallic
      * @description Metallic texture (PBR)
      */
-    metallic?: File_1;
+    metallic?: File;
     /**
      * Normal
      * @description Normal texture (PBR)
      */
-    normal?: File_1;
+    normal?: File;
     /**
      * Roughness
      * @description Roughness texture (PBR)
      */
-    roughness?: File_1;
+    roughness?: File;
 }
 
 export interface TextRender {
@@ -998,6 +1067,21 @@ export interface SigmasInput {
     method?: 'default' | 'array';
 }
 
+export interface Shot {
+    /**
+     * Num Frames
+     * @description Number of frames for this shot. Each shot must have between 17 and 100 frames.
+     * @default 65
+     */
+    num_frames?: number;
+    /**
+     * Prompt
+     * @description Caption describing what happens in this shot, including subject actions, camera angles, and scene details.
+     * @example Subject 1 is smiling and gesturing with his right hand while facing the camera. Subject 2 is seen from behind, facing Subject 1. The scene is indoors in a well-decorated room, with a dark door and ornate glass visible in the background. The camera is static, providing a medium close-up shot of Subject 1.
+     */
+    prompt: string;
+}
+
 export interface SemanticImageInput {
     /**
      * Hypothesis
@@ -1374,7 +1458,6 @@ export interface PointPromptBase {
     /**
      * Label
      * @description 1 for foreground, 0 for background
-     * @enum {integer}
      */
     label?: 0 | 1;
     /**
@@ -1431,7 +1514,6 @@ export interface PointPrompt {
     /**
      * Label
      * @description 1 for foreground, 0 for background
-     * @enum {integer}
      */
     label?: 0 | 1;
     /**
@@ -1634,24 +1716,6 @@ export interface Object {
     y_min: number;
 }
 
-export interface NovaSRTimings {
-    /**
-     * Inference
-     * @description Time taken to run the inference in seconds.
-     */
-    inference: number;
-    /**
-     * Postprocess
-     * @description Time taken to postprocess the audio in seconds.
-     */
-    postprocess: number;
-    /**
-     * Preprocess
-     * @description Time taken to preprocess the audio in seconds.
-     */
-    preprocess: number;
-}
-
 export interface MusicSection {
     /**
      * Duration Ms
@@ -1719,22 +1783,22 @@ export interface ModelUrls_2 {
      * Fbx
      * @description FBX format 3D model
      */
-    fbx?: File_1;
+    fbx?: File;
     /**
      * Glb
      * @description GLB format 3D model
      */
-    glb?: File_1;
+    glb?: File;
     /**
      * Obj
      * @description OBJ format 3D model
      */
-    obj?: File_1;
+    obj?: File;
     /**
      * Usdz
      * @description USDZ format 3D model
      */
-    usdz?: File_1;
+    usdz?: File;
 }
 
 export interface ModelUrls_1 {
@@ -1742,32 +1806,32 @@ export interface ModelUrls_1 {
      * Fbx
      * @description FBX format 3D model
      */
-    fbx?: File_1;
+    fbx?: File;
     /**
      * Glb
      * @description GLB format 3D model
      */
-    glb?: File_1;
+    glb?: File;
     /**
      * Mtl
      * @description MTL material file for OBJ model
      */
-    mtl?: File_1;
+    mtl?: File;
     /**
      * Obj
      * @description OBJ format 3D model
      */
-    obj?: File_1;
+    obj?: File;
     /**
      * Texture
      * @description Texture image for the 3D model
      */
-    texture?: File_1;
+    texture?: File;
     /**
      * Usdz
      * @description USDZ format 3D model
      */
-    usdz?: File_1;
+    usdz?: File;
 }
 
 export interface ModelUrls {
@@ -1775,32 +1839,32 @@ export interface ModelUrls {
      * Blend
      * @description Blender format 3D model
      */
-    blend?: File_1;
+    blend?: File;
     /**
      * Fbx
      * @description FBX format 3D model
      */
-    fbx?: File_1;
+    fbx?: File;
     /**
      * Glb
      * @description GLB format 3D model
      */
-    glb?: File_1;
+    glb?: File;
     /**
      * Obj
      * @description OBJ format 3D model
      */
-    obj?: File_1;
+    obj?: File;
     /**
      * Stl
      * @description STL format 3D model
      */
-    stl?: File_1;
+    stl?: File;
     /**
      * Usdz
      * @description USDZ format 3D model
      */
-    usdz?: File_1;
+    usdz?: File;
 }
 
 export interface MaskMetadata {
@@ -2136,6 +2200,24 @@ export interface Lighting {
     shadows?: string;
 }
 
+export interface LavaSRTimings {
+    /**
+     * Inference
+     * @description Time taken to run the inference in seconds.
+     */
+    inference: number;
+    /**
+     * Postprocess
+     * @description Time taken to postprocess the audio in seconds.
+     */
+    postprocess: number;
+    /**
+     * Preprocess
+     * @description Time taken to preprocess the audio in seconds.
+     */
+    preprocess: number;
+}
+
 export interface KlingV3MultiPromptElement {
     /**
      * Duration
@@ -2755,6 +2837,12 @@ export interface File_1 {
      * @example image/png
      */
     content_type?: string;
+    /**
+     * File Data
+     * Format: binary
+     * @description File data
+     */
+    file_data?: string;
     /**
      * File Name
      * @description The name of the file. It will be auto-generated if not provided.
@@ -2781,12 +2869,6 @@ export interface File {
      * @example image/png
      */
     content_type?: string;
-    /**
-     * File Data
-     * Format: binary
-     * @description File data
-     */
-    file_data?: string;
     /**
      * File Name
      * @description The name of the file. It will be auto-generated if not provided.
@@ -2909,7 +2991,7 @@ export interface EmotionalStrengths {
     surprised?: number;
 }
 
-export interface Embedding_1 {
+export interface Embedding_2 {
     /**
      * Path
      * @description URL or the path to the embedding weights.
@@ -2926,6 +3008,31 @@ export interface Embedding_1 {
     tokens?: string[];
 }
 
+export interface Embedding_1 {
+    /**
+     * Force
+     * @description If set to true, the embedding will be forced to be used.
+     * @default false
+     */
+    force?: boolean;
+    /**
+     * Path
+     * @description URL or the path to the embedding weights.
+     * @example https://civitai.com/api/download/models/135931
+     * @example https://filebin.net/3chfqasxpqu21y8n/my-custom-lora-v1.safetensors
+     */
+    path: string;
+    /**
+     * Tokens
+     * @description The list of tokens to use for the embedding.
+     * @default [
+     *       "<s0>",
+     *       "<s1>"
+     *     ]
+     */
+    tokens?: string[];
+}
+
 export interface Embedding {
     /**
      * Path
@@ -3025,7 +3132,7 @@ export interface DiarizationSegment {
      * Timestamp
      * @description Start and end timestamp of the segment
      */
-    timestamp: { [x: string]: any }[];
+    timestamp: [number, number];
 }
 
 export interface DialogueBlock {
@@ -3745,12 +3852,6 @@ export interface AudioFile {
      * @description The duration of the audio
      */
     duration?: number;
-    /**
-     * File Data
-     * Format: binary
-     * @description File data
-     */
-    file_data?: string;
     /**
      * File Name
      * @description The name of the file. It will be auto-generated if not provided.

package/types/fal/endpoints/index.d.ts

@@ -624,6 +624,11 @@ declare global {
                 output: { [x in string]: any };
             };
 
+            'fal-ai/wan-motion': {
+                input: falEndpoints.WanMotionInput;
+                output: falEndpoints.WanMotionOutput;
+            };
+
             'fal-ai/wan-i2v-lora': {
                 input: falEndpoints.WanI2vLoraInput;
                 output: falEndpoints.WanI2vLoraOutput;
@@ -704,6 +709,16 @@ declare global {
                 output: falEndpoints.Wan22VaceFunA14bDepthOutput;
             };
 
+            'fal-ai/wan-22-trainer/t2v-a14b': {
+                input: falEndpoints.Wan22TrainerT2vA14bInput;
+                output: falEndpoints.Wan22TrainerT2vA14bOutput;
+            };
+
+            'fal-ai/wan-22-trainer/i2v-a14b': {
+                input: falEndpoints.Wan22TrainerI2vA14bInput;
+                output: falEndpoints.Wan22TrainerI2vA14bOutput;
+            };
+
             'fal-ai/wan-22-image-trainer': {
                 input: falEndpoints.Wan22ImageTrainerInput;
                 output: falEndpoints.Wan22ImageTrainerOutput;
@@ -2169,6 +2184,11 @@ declare global {
                 output: falEndpoints.MusetalkOutput;
             };
 
+            'fal-ai/multishot-master': {
+                input: falEndpoints.MultishotMasterInput;
+                output: falEndpoints.MultishotMasterOutput;
+            };
+
             'fal-ai/moondream3-preview/segment': {
                 input: { [x in string]: any };
                 output: { [x in string]: any };
@@ -2910,8 +2930,8 @@ declare global {
             };
 
             'fal-ai/live-portrait/image': {
-                input: { [x in string]: any };
-                output: { [x in string]: any };
+                input: falEndpoints.LivePortraitImageInput;
+                output: falEndpoints.LivePortraitImageOutput;
             };
 
             'fal-ai/live-portrait': {
@@ -2964,6 +2984,11 @@ declare global {
                 output: falEndpoints.LayerDiffusionOutput;
             };
 
+            'fal-ai/lava-sr': {
+                input: falEndpoints.LavaSrInput;
+                output: falEndpoints.LavaSrOutput;
+            };
+
             'fal-ai/latentsync': {
                 input: falEndpoints.LatentsyncInput;
                 output: falEndpoints.LatentsyncOutput;
@@ -5244,6 +5269,26 @@ declare global {
                 output: falEndpoints.CreatifyAuroraOutput;
             };
 
+            'fal-ai/cosmos-predict-2.5/video-to-video': {
+                input: falEndpoints.CosmosPredict25VideoToVideoInput;
+                output: falEndpoints.CosmosPredict25VideoToVideoOutput;
+            };
+
+            'fal-ai/cosmos-predict-2.5/text-to-video': {
+                input: falEndpoints.CosmosPredict25TextToVideoInput;
+                output: falEndpoints.CosmosPredict25TextToVideoOutput;
+            };
+
+            'fal-ai/cosmos-predict-2.5/image-to-video': {
+                input: falEndpoints.CosmosPredict25ImageToVideoInput;
+                output: falEndpoints.CosmosPredict25ImageToVideoOutput;
+            };
+
+            'fal-ai/cosmos-predict-2.5/distilled/text-to-video': {
+                input: falEndpoints.CosmosPredict25DistilledTextToVideoInput;
+                output: falEndpoints.CosmosPredict25DistilledTextToVideoOutput;
+            };
+
             'fal-ai/controlnext': {
                 input: falEndpoints.ControlnextInput;
                 output: falEndpoints.ControlnextOutput;
@@ -5344,6 +5389,16 @@ declare global {
                 output: falEndpoints.BytedanceVideoStylizeOutput;
             };
 
+            'fal-ai/bytedance/seedream/v5/lite/text-to-image': {
+                input: falEndpoints.BytedanceSeedreamV5LiteTextToImageInput;
+                output: falEndpoints.BytedanceSeedreamV5LiteTextToImageOutput;
+            };
+
+            'fal-ai/bytedance/seedream/v5/lite/edit': {
+                input: falEndpoints.BytedanceSeedreamV5LiteEditInput;
+                output: falEndpoints.BytedanceSeedreamV5LiteEditOutput;
+            };
+
             'fal-ai/bytedance/seedream/v4/text-to-image': {
                 input: falEndpoints.BytedanceSeedreamV4TextToImageInput;
                 output: falEndpoints.BytedanceSeedreamV4TextToImageOutput;
@@ -5489,6 +5544,11 @@ declare global {
                 output: falEndpoints.BriaBackgroundRemoveOutput;
             };
 
+            'fal-ai/bitdance': {
+                input: falEndpoints.BitdanceInput;
+                output: falEndpoints.BitdanceOutput;
+            };
+
             'fal-ai/birefnet/v2/video': {
                 input: falEndpoints.BirefnetV2VideoInput;
                 output: falEndpoints.BirefnetV2VideoOutput;
@@ -5629,6 +5689,11 @@ declare global {
                 output: falEndpoints.DecartLucyRestyleOutput;
             };
 
+            'decart/lucy-i2v': {
+                input: falEndpoints.DecartLucyI2vInput;
+                output: falEndpoints.DecartLucyI2vOutput;
+            };
+
             'decart/lucy-edit/pro': {
                 input: falEndpoints.DecartLucyEditProInput;
                 output: falEndpoints.DecartLucyEditProOutput;
@@ -5644,11 +5709,6 @@ declare global {
                 output: falEndpoints.DecartLucyEditDevOutput;
             };
 
-            'decart/lucy-14b/image-to-video': {
-                input: falEndpoints.DecartLucy14bImageToVideoInput;
-                output: falEndpoints.DecartLucy14bImageToVideoOutput;
-            };
-
             'clarityai/crystal-video-upscaler': {
                 input: falEndpoints.ClarityaiCrystalVideoUpscalerInput;
                 output: falEndpoints.ClarityaiCrystalVideoUpscalerOutput;
@@ -5704,6 +5764,11 @@ declare global {
                 output: falEndpoints.BriaVideoBackgroundRemovalOutput;
             };
 
+            'bria/upscale/creative': {
+                input: falEndpoints.BriaUpscaleCreativeInput;
+                output: falEndpoints.BriaUpscaleCreativeOutput;
+            };
+
             'bria/text-to-image/3.2': {
                 input: falEndpoints.BriaTextToImage32Input;
                 output: falEndpoints.BriaTextToImage32Output;