@scenario-labs/sdk 0.3.0 → 1.1.0

package/src/resources/models/models.ts

@@ -38,6 +38,7 @@ import {
   TrainingImages,
 } from './training-images';
 import { APIPromise } from '../../core/api-promise';
+import { ModelsCursor, type ModelsCursorParams, PagePromise } from '../../core/pagination';
 import { RequestOptions } from '../../internal/request-options';
 import { path } from '../../internal/utils/path';
 
@@ -88,8 +89,8 @@ export class Models extends APIResource {
   list(
     query: ModelListParams | null | undefined = {},
     options?: RequestOptions,
-  ): APIPromise<ModelListResponse> {
-    return this._client.get('/models', { query, ...options });
+  ): PagePromise<ModelListResponsesModelsCursor, ModelListResponse> {
+    return this._client.getAPIList('/models', ModelsCursor<ModelListResponse>, { query, ...options });
   }
 
   /**
@@ -163,6 +164,8 @@ export class Models extends APIResource {
   }
 }
 
+export type ModelListResponsesModelsCursor = ModelsCursor<ModelListResponse>;
+
 export interface ModelCreateResponse {
   model: ModelCreateResponse.Model;
 }
@@ -181,6 +184,7 @@ export namespace ModelCreateResponse {
     capabilities: Array<
       | '3d23d'
       | 'audio2audio'
+      | 'audio2video'
       | 'controlnet'
       | 'controlnet_img2img'
       | 'controlnet_inpaint'
@@ -207,6 +211,7 @@ export namespace ModelCreateResponse {
       | 'txt2txt'
       | 'txt2video'
       | 'video23d'
+      | 'video2audio'
       | 'video2img'
       | 'video2video'
     >;
@@ -1477,6 +1482,7 @@ export namespace ModelRetrieveResponse {
     capabilities: Array<
       | '3d23d'
       | 'audio2audio'
+      | 'audio2video'
       | 'controlnet'
       | 'controlnet_img2img'
       | 'controlnet_inpaint'
@@ -1503,6 +1509,7 @@ export namespace ModelRetrieveResponse {
       | 'txt2txt'
       | 'txt2video'
       | 'video23d'
+      | 'video2audio'
       | 'video2img'
       | 'video2video'
     >;
@@ -2773,6 +2780,7 @@ export namespace ModelUpdateResponse {
     capabilities: Array<
       | '3d23d'
       | 'audio2audio'
+      | 'audio2video'
       | 'controlnet'
       | 'controlnet_img2img'
       | 'controlnet_inpaint'
@@ -2799,6 +2807,7 @@ export namespace ModelUpdateResponse {
       | 'txt2txt'
       | 'txt2video'
       | 'video23d'
+      | 'video2audio'
       | 'video2img'
       | 'video2video'
     >;
@@ -4052,117 +4061,510 @@ export namespace ModelUpdateResponse {
 }
 
 export interface ModelListResponse {
-  models: Array<ModelListResponse.Model>;
+  /**
+   * The model ID (example: "model_eyVcnFJcR92BxBkz7N6g5w")
+   */
+  id: string;
+
+  /**
+   * List of model capabilities (example: ["txt2img", "img2img",
+   * "txt2img_ip_adapter", ...])
+   */
+  capabilities: Array<
+    | '3d23d'
+    | 'audio2audio'
+    | 'audio2video'
+    | 'controlnet'
+    | 'controlnet_img2img'
+    | 'controlnet_inpaint'
+    | 'controlnet_inpaint_ip_adapter'
+    | 'controlnet_ip_adapter'
+    | 'controlnet_reference'
+    | 'controlnet_texture'
+    | 'img23d'
+    | 'img2img'
+    | 'img2img_ip_adapter'
+    | 'img2img_texture'
+    | 'img2txt'
+    | 'img2video'
+    | 'inpaint'
+    | 'inpaint_ip_adapter'
+    | 'outpaint'
+    | 'reference'
+    | 'reference_texture'
+    | 'txt23d'
+    | 'txt2audio'
+    | 'txt2img'
+    | 'txt2img_ip_adapter'
+    | 'txt2img_texture'
+    | 'txt2txt'
+    | 'txt2video'
+    | 'video23d'
+    | 'video2audio'
+    | 'video2img'
+    | 'video2video'
+  >;
+
+  /**
+   * A list of CollectionId this model belongs to
+   */
+  collectionIds: Array<string>;
+
+  /**
+   * The model creation date as an ISO string (example: "2023-02-03T11:19:41.579Z")
+   */
+  createdAt: string;
+
+  /**
+   * Whether the model is a custom model and can be used only with POST
+   * /generate/custom/{modelId} endpoint
+   */
+  custom: boolean;
+
+  /**
+   * List of all example asset IDs setup by the model owner
+   */
+  exampleAssetIds: Array<string>;
+
+  /**
+   * The privacy of the model (default: private)
+   */
+  privacy: 'private' | 'public' | 'unlisted';
+
+  /**
+   * The source of the model
+   */
+  source: 'civitai' | 'huggingface' | 'other' | 'scenario';
+
+  /**
+   * The model status
+   */
+  status: 'copying' | 'failed' | 'new' | 'trained' | 'training' | 'training-canceled';
+
+  /**
+   * The associated tags (example: ["sci-fi", "landscape"])
+   */
+  tags: Array<string>;
+
+  /**
+   * The total number of training images
+   */
+  trainingImagesNumber: number;
+
+  /**
+   * The model type (example: "flux.1-lora")
+   */
+  type:
+    | 'custom'
+    | 'elevenlabs-voice'
+    | 'flux.1'
+    | 'flux.1-composition'
+    | 'flux.1-kontext-dev'
+    | 'flux.1-kontext-lora'
+    | 'flux.1-krea-dev'
+    | 'flux.1-krea-lora'
+    | 'flux.1-lora'
+    | 'flux.1-pro'
+    | 'flux.1.1-pro-ultra'
+    | 'flux.2-dev-edit-lora'
+    | 'flux.2-dev-lora'
+    | 'flux.2-klein-4b-edit-lora'
+    | 'flux.2-klein-4b-lora'
+    | 'flux.2-klein-9b-edit-lora'
+    | 'flux.2-klein-9b-lora'
+    | 'flux.2-klein-base-4b-edit-lora'
+    | 'flux.2-klein-base-4b-lora'
+    | 'flux.2-klein-base-9b-edit-lora'
+    | 'flux.2-klein-base-9b-lora'
+    | 'flux1.1-pro'
+    | 'gpt-image-1'
+    | 'qwen-image-2512-lora'
+    | 'qwen-image-edit-2509-lora'
+    | 'qwen-image-edit-2511-lora'
+    | 'qwen-image-edit-lora'
+    | 'qwen-image-lora'
+    | 'sd-1_5'
+    | 'sd-1_5-composition'
+    | 'sd-1_5-lora'
+    | 'sd-xl'
+    | 'sd-xl-composition'
+    | 'sd-xl-lora'
+    | 'zimage-de-turbo-lora'
+    | 'zimage-lora'
+    | 'zimage-turbo-lora';
+
+  /**
+   * The model last update date as an ISO string (example:
+   * "2023-02-03T11:19:41.579Z")
+   */
+  updatedAt: string;
+
+  /**
+   * The access restrictions of the model 0: Free plan 25: Creator plan 50: Pro plan
+   * 75: Team plan 100: Enterprise plan
+   */
+  accessRestrictions?: 0 | 100 | 25 | 50 | 75;
+
+  /**
+   * The author user ID (example: "user_VFhihHKMRZyDDnZAJwLb2Q")
+   */
+  authorId?: string;
+
+  /**
+   * The class of the model
+   */
+  class?: ModelListResponse.Class;
+
+  /**
+   * List of base model IDs compliant with the model (example: ["flux.1-dev",
+   * "flux.1-schnell"]) This attribute is mainly used for Flux LoRA models
+   */
+  compliantModelIds?: Array<string>;
+
+  /**
+   * The concepts is required for the type model: composition
+   */
+  concepts?: Array<ModelListResponse.Concept>;
+
+  /**
+   * The epoch of the model. Only available for Flux Lora Trained models. If not set,
+   * uses the final model epoch (latest)
+   */
+  epoch?: string;
+
+  /**
+   * The epochs of the model. Only available for Flux Lora Trained models.
+   */
+  epochs?: Array<ModelListResponse.Epoch>;
+
+  /**
+   * The inputs of the model. Only used for custom models. To retrieve this list, get
+   * it by modelId with GET /models/{modelId}
+   */
+  inputs?: Array<ModelListResponse.Input>;
+
+  /**
+   * The model keyword, this is a legacy parameter, please use conceptPrompt in
+   * parameters
+   */
+  modelKeyword?: string;
+
+  /**
+   * The model name (example: "Cinematic Realism")
+   */
+  name?: string;
+
+  /**
+   * Fine-tune the model's inferences with negative prompt embedding
+   */
+  negativePromptEmbedding?: string;
+
+  /**
+   * The owner ID (example: "team_VFhihHKMRZyDDnZAJwLb2Q")
+   */
+  ownerId?: string;
+
+  /**
+   * The parameters of the model
+   */
+  parameters?: ModelListResponse.Parameters;
+
+  /**
+   * The id of the parent model
+   */
+  parentModelId?: string;
+
+  /**
+   * Aggregated performance stats
+   */
+  performanceStats?: ModelListResponse.PerformanceStats;
+
+  /**
+   * Fine-tune the model's inferences with prompt embedding
+   */
+  promptEmbedding?: string;
 
   /**
-   * A token to query the next page of models
+   * The model short description (example: "This model generates highly detailed
+   * cinematic scenes.")
    */
-  nextPaginationToken?: string;
+  shortDescription?: string;
+
+  /**
+   * The date when the model will be soft deleted (only for Free plan)
+   */
+  softDeletionOn?: string;
+
+  /**
+   * A thumbnail for your model
+   */
+  thumbnail?: ModelListResponse.Thumbnail;
+
+  /**
+   * Array of training image pairs
+   */
+  trainingImagePairs?: Array<ModelListResponse.TrainingImagePair>;
+
+  /**
+   * The URLs of the first 3 training images of the model. To retrieve the full set
+   * of images, get it by modelId
+   */
+  trainingImages?: Array<ModelListResponse.TrainingImage>;
+
+  /**
+   * Additional information about the training progress of the model
+   */
+  trainingProgress?: ModelListResponse.TrainingProgress;
+
+  /**
+   * Additional information about the model's training
+   */
+  trainingStats?: ModelListResponse.TrainingStats;
+
+  /**
+   * The UI configuration for the model
+   */
+  uiConfig?: ModelListResponse.UiConfig;
+
+  /**
+   * (Deprecated) The user ID (example: "user_VFhihHKMRZyDDnZAJwLb2Q")
+   */
+  userId?: string;
 }
 
 export namespace ModelListResponse {
-  export interface Model {
+  /**
+   * The class of the model
+   */
+  export interface Class {
     /**
-     * The model ID (example: "model_eyVcnFJcR92BxBkz7N6g5w")
+     * The category slug of the class (example: "art-style")
      */
-    id: string;
+    category: string;
 
     /**
-     * List of model capabilities (example: ["txt2img", "img2img",
-     * "txt2img_ip_adapter", ...])
+     * The concept prompt of the class (example: "a sks character design")
      */
-    capabilities: Array<
-      | '3d23d'
-      | 'audio2audio'
-      | 'controlnet'
-      | 'controlnet_img2img'
-      | 'controlnet_inpaint'
-      | 'controlnet_inpaint_ip_adapter'
-      | 'controlnet_ip_adapter'
-      | 'controlnet_reference'
-      | 'controlnet_texture'
-      | 'img23d'
-      | 'img2img'
-      | 'img2img_ip_adapter'
-      | 'img2img_texture'
-      | 'img2txt'
-      | 'img2video'
-      | 'inpaint'
-      | 'inpaint_ip_adapter'
-      | 'outpaint'
-      | 'reference'
-      | 'reference_texture'
-      | 'txt23d'
-      | 'txt2audio'
-      | 'txt2img'
-      | 'txt2img_ip_adapter'
-      | 'txt2img_texture'
-      | 'txt2txt'
-      | 'txt2video'
-      | 'video23d'
-      | 'video2img'
-      | 'video2video'
-    >;
+    conceptPrompt: string;
 
     /**
-     * A list of CollectionId this model belongs to
+     * The model ID of the class (example: "stable-diffusion-v1-5")
      */
-    collectionIds: Array<string>;
+    modelId: string;
 
     /**
-     * The model creation date as an ISO string (example: "2023-02-03T11:19:41.579Z")
+     * The class name (example: "Character Design")
      */
-    createdAt: string;
+    name: string;
 
     /**
-     * Whether the model is a custom model and can be used only with POST
-     * /generate/custom/{modelId} endpoint
+     * The class prompt (example: "a character design")
      */
-    custom: boolean;
+    prompt: string;
 
     /**
-     * List of all example asset IDs setup by the model owner
+     * The class slug (example: "art-style-character-design")
      */
-    exampleAssetIds: Array<string>;
+    slug: string;
 
     /**
-     * The privacy of the model (default: private)
+     * The class status (only published classes are listed, but unpublished classes can
+     * still appear in existing models)
      */
-    privacy: 'private' | 'public' | 'unlisted';
+    status: 'published' | 'unpublished';
 
     /**
-     * The source of the model
+     * Some example images URLs to showcase the class
      */
-    source: 'civitai' | 'huggingface' | 'other' | 'scenario';
+    thumbnails: Array<string>;
+  }
 
+  export interface Concept {
     /**
-     * The model status
+     * The model ID (example: "model_eyVcnFJcR92BxBkz7N6g5w")
      */
-    status: 'copying' | 'failed' | 'new' | 'trained' | 'training' | 'training-canceled';
+    modelId: string;
 
     /**
-     * The associated tags (example: ["sci-fi", "landscape"])
+     * The scale of the model (example: 1.0) For Flux Kontext Prompt Editing, the scale
+     * is between 0 and 2.
      */
-    tags: Array<string>;
+    scale: number;
 
     /**
-     * The total number of training images
+     * The epoch of the model (example: "000001") Only available for Flux Lora Trained
+     * models
      */
-    trainingImagesNumber: number;
+    modelEpoch?: string;
+  }
 
+  export interface Epoch {
     /**
-     * The model type (example: "flux.1-lora")
+     * The epoch hash to identify the epoch
+     */
+    epoch: string;
+
+    /**
+     * The assets of the epoch if sample prompts as been supplied during training
+     */
+    assets?: Array<Epoch.Asset>;
+  }
+
+  export namespace Epoch {
+    export interface Asset {
+      /**
+       * The AssetId of the image during training (example:
+       * "asset_GTrL3mq4SXWyMxkOHRxlpw")
+       */
+      assetId: string;
+
+      /**
+       * The url of the asset
+       */
+      url: string;
+    }
+  }
+
+  /**
+   * Defines the input parameters for a model. Use this to understand the available
+   * input parameters for a given `modelId` when calling
+   * `POST /generate/custom/{modelId}`. See {@link
+   * https://docs.scenario.com/docs/video-generation} for examples.
+   */
+  export interface Input {
+    /**
+     * The name that must be user to call the model through the API
+     */
+    name: string;
+
+    /**
+     * The data type of the input
      */
     type:
-      | 'custom'
-      | 'elevenlabs-voice'
-      | 'flux.1'
-      | 'flux.1-composition'
-      | 'flux.1-kontext-dev'
-      | 'flux.1-kontext-lora'
-      | 'flux.1-krea-dev'
-      | 'flux.1-krea-lora'
-      | 'flux.1-lora'
+      | 'boolean'
+      | 'file'
+      | 'file_array'
+      | 'inputs_array'
+      | 'model'
+      | 'model_array'
+      | 'number'
+      | 'number_array'
+      | 'string'
+      | 'string_array';
+
+    /**
+     * The allowed values for the input. For \`string\` or \`number\` types, creates a
+     * single-select dropdown. For \`string_array\` type, creates a multi-select
+     * dropdown.
+     */
+    allowedValues?: Array<unknown>;
+
+    /**
+     * Specifies the background behavior for the input. Only available for \`file\` and
+     * \`file_array\` input types with kind \`image\`.
+     */
+    backgroundBehavior?: 'opaque' | 'transparent';
+
+    /**
+     * Whether the input is a color or not. Only available for \`string\` input type.
+     */
+    color?: boolean;
+
+    /**
+     * Whether this input affects the model's cost calculation
+     */
+    costImpact?: boolean;
+
+    /**
+     * The default value for the input
+     */
+    default?: unknown;
+
+    /**
+     * Help text displayed in the UI to provide additional information about the input
+     */
+    description?: string;
+
+    /**
+     * Used to visually group inputs together in the UI. Inputs with the same group
+     * value appear consecutively in the UI.
+     */
+    group?: string;
+
+    /**
+     * Hint text displayed in the UI as a tooltip to guide the user
+     */
+    hint?: string;
+
+    /**
+     * The list of inputs which form an object within a container array. All inputs are
+     * the same as the current object. This is only available for type inputs_array
+     * inputs.
+     */
+    inputs?: Array<{ [key: string]: unknown }>;
+
+    /**
+     * The asset kind of the input. Only taken into account for \`file\` and
+     * \`file_array\` input types. If model provides multiple kinds, the input will be
+     * not able to create the asset on the flight on API side with dataurl without
+     * data:kind, prefix
+     */
+    kind?: '3d' | 'audio' | 'document' | 'image' | 'image-hdr' | 'json' | 'video';
+
+    /**
+     * The label displayed in the UI for this input
+     */
+    label?: string;
+
+    /**
+     * The name of the file input field to use as the mask source
+     */
+    maskFrom?: string;
+
+    /**
+     * The maximum allowed value. Only available for \`number\` and \`array\` input
+     * types.
+     */
+    max?: number;
+
+    /**
+     * The maximum allowed length for \`string\` inputs. Also applies to each item in
+     * \`string_array\`.
+     */
+    maxLength?: number;
+
+    /**
+     * The maximum allowed file size in bytes. Only applies to \`file\` and
+     * \`file_array\` input types. Validated against \`asset.properties.size\` at job
+     * creation time.
+     */
+    maxSize?: number;
+
+    /**
+     * The minimum allowed value. Only available for \`number\` and array input types.
+     */
+    min?: number;
+
+    /**
+     * The minimum allowed length for string inputs. Also applies to each item in
+     * \`string_array\`.
+     */
+    minLength?: number;
+
+    /**
+     * The allowed model types for this input. Example: \`["flux.1-lora"]\`. Only
+     * available for \`model_array\` input type.
+     */
+    modelTypes?: Array<
+      | 'custom'
+      | 'elevenlabs-voice'
+      | 'flux.1'
+      | 'flux.1-composition'
+      | 'flux.1-kontext-dev'
+      | 'flux.1-kontext-lora'
+      | 'flux.1-krea-dev'
+      | 'flux.1-krea-lora'
+      | 'flux.1-lora'
       | 'flux.1-pro'
       | 'flux.1.1-pro-ultra'
       | 'flux.2-dev-edit-lora'
@@ -4190,1165 +4592,763 @@ export namespace ModelListResponse {
       | 'sd-xl-lora'
       | 'zimage-de-turbo-lora'
       | 'zimage-lora'
-      | 'zimage-turbo-lora';
+      | 'zimage-turbo-lora'
+    >;
 
     /**
-     * The model last update date as an ISO string (example:
-     * "2023-02-03T11:19:41.579Z")
+     * Whether this input represents a parent asset to assign to the produced assets.
+     * Only available for \`file\` and \`file_array\` input types.
+     *
+     * For \`file_array\`, the parent asset is the first item in the array.
      */
-    updatedAt: string;
+    parent?: boolean;
 
     /**
-     * The access restrictions of the model 0: Free plan 25: Creator plan 50: Pro plan
-     * 75: Team plan 100: Enterprise plan
+     * Placeholder text for the input. Only available for 'string' input type.
      */
-    accessRestrictions?: 0 | 100 | 25 | 50 | 75;
+    placeholder?: string;
 
     /**
-     * The author user ID (example: "user_VFhihHKMRZyDDnZAJwLb2Q")
+     * Whether the input is a prompt. When true, displays as a text area with prompt
+     * spark feature. Only available for \`string\` input type.
      */
-    authorId?: string;
+    prompt?: boolean;
 
     /**
-     * The class of the model
+     * Whether the input is used with prompt spark. Only available for \`string\` input
+     * type.
      */
-    class?: Model.Class;
+    promptSpark?: boolean;
 
     /**
-     * List of base model IDs compliant with the model (example: ["flux.1-dev",
-     * "flux.1-schnell"]) This attribute is mainly used for Flux LoRA models
+     * Set of rules that describes when this input is required:
+     *
+     * - \`always\`: Input is always required
+     * - \`ifNotDefined\`: Input is required when another specified input is not
+     *   defined
+     * - \`ifDefined\`: Input is required when another specified input is defined
+     * - \`conditionalValues\`: Input is required when another input has a specific
+     *   value
+     *
+     * By default, the input is not required.
      */
-    compliantModelIds?: Array<string>;
+    required?: Input.Required;
 
     /**
-     * The concepts is required for the type model: composition
+     * The step increment for numeric inputs. Only available for \`number\` input type.
      */
-    concepts?: Array<Model.Concept>;
+    step?: number;
+  }
 
+  export namespace Input {
     /**
-     * The epoch of the model. Only available for Flux Lora Trained models. If not set,
-     * uses the final model epoch (latest)
+     * Set of rules that describes when this input is required:
+     *
+     * - \`always\`: Input is always required
+     * - \`ifNotDefined\`: Input is required when another specified input is not
+     *   defined
+     * - \`ifDefined\`: Input is required when another specified input is defined
+     * - \`conditionalValues\`: Input is required when another input has a specific
+     *   value
+     *
+     * By default, the input is not required.
      */
-    epoch?: string;
+    export interface Required {
+      /**
+       * Whether the input is always required
+       */
+      always?: boolean;
 
-    /**
-     * The epochs of the model. Only available for Flux Lora Trained models.
-     */
-    epochs?: Array<Model.Epoch>;
+      /**
+       * Makes this input required when another input has a specific value:
+       *
+       * - Key: name of the input to check
+       * - Value: operation and allowed values that trigger the requirement
+       */
+      conditionalValues?: unknown;
+
+      /**
+       * Makes this input required when another input is defined:
+       *
+       * - Key: name of the input that must be defined
+       * - Value: message to display when this input is required
+       */
+      ifDefined?: unknown;
+
+      /**
+       * Makes this input required when another input is not defined:
+       *
+       * - Key: name of the input that must be undefined
+       * - Value: message to display when this input is required
+       */
+      ifNotDefined?: unknown;
+    }
+  }
 
+  /**
+   * The parameters of the model
+   */
+  export interface Parameters {
     /**
-     * The inputs of the model. Only used for custom models. To retrieve this list, get
-     * it by modelId with GET /models/{modelId}
+     * Age group of the voice (for professional cloning)
+     *
+     * Only available for ElevenLabs voice training
      */
-    inputs?: Array<Model.Input>;
+    age?: string;
 
     /**
-     * The model keyword, this is a legacy parameter, please use conceptPrompt in
-     * parameters
+     * The batch size Less steps, and will increase the learning rate
+     *
+     * Only available for Flux LoRA training
      */
-    modelKeyword?: string;
+    batchSize?: number;
 
     /**
-     * The model name (example: "Cinematic Realism")
+     * The prompt to specify images in the same class as provided instance images
+     *
+     * Only available for SD15 training
      */
-    name?: string;
+    classPrompt?: string;
 
     /**
-     * Fine-tune the model's inferences with negative prompt embedding
+     * Type of voice cloning: "instant" (fast) or "professional" (higher quality,
+     * requires captcha)
+     *
+     * Only available for ElevenLabs voice training
      */
-    negativePromptEmbedding?: string;
+    cloneType?: string;
 
     /**
-     * The owner ID (example: "team_VFhihHKMRZyDDnZAJwLb2Q")
+     * The prompt with identifier specifying the instance (or subject) of the class
+     * (example: "a daiton dog")
+     *
+     * Default value varies depending on the model type:
+     *
+     * - For SD1.5: "daiton" if no class is associated with the model
+     * - For SDXL: "daiton"
+     * - For Flux: ""
      */
-    ownerId?: string;
+    conceptPrompt?: string;
 
     /**
-     * The parameters of the model
+     * Gender of the voice (for professional cloning)
+     *
+     * Only available for ElevenLabs voice training
      */
-    parameters?: Model.Parameters;
+    gender?: string;
 
     /**
-     * The id of the parent model
+     * Language of the audio samples (ISO 639-1 code)
+     *
+     * Only available for ElevenLabs voice training
      */
-    parentModelId?: string;
+    language?: string;
 
     /**
-     * Aggregated performance stats
+     * Initial learning rate (after the potential warmup period)
+     *
+     * Default value varies depending on the model type:
+     *
+     * - For SD1.5 and SDXL: 0.000005
+     * - For Flux: 0.0001
      */
-    performanceStats?: Model.PerformanceStats;
+    learningRate?: number;
 
     /**
-     * Fine-tune the model's inferences with prompt embedding
+     * Initial learning rate (after the potential warmup period) for the text encoder
+     *
+     * Maximum [Flux LoRA: 0.001] Default [SDXL: 0.00005 | Flux LoRA: 0.00001] Minimum
+     * [SDXL: 0 | Flux LoRA: 0.000001]
      */
-    promptEmbedding?: string;
+    learningRateTextEncoder?: number;
 
     /**
-     * The model short description (example: "This model generates highly detailed
-     * cinematic scenes.")
+     * Initial learning rate (after the potential warmup period) for the UNet
+     *
+     * Only available for SDXL LoRA training
      */
-    shortDescription?: string;
+    learningRateUnet?: number;
 
     /**
-     * The date when the model will be soft deleted (only for Free plan)
+     * The scheduler type to use (default: "constant")
+     *
+     * Only available for SD15 and SDXL LoRA training
      */
-    softDeletionOn?: string;
+    lrScheduler?:
+      | 'constant'
+      | 'constant-with-warmup'
+      | 'cosine'
+      | 'cosine-with-restarts'
+      | 'linear'
+      | 'polynomial';
 
     /**
-     * A thumbnail for your model
+     * Maximum number of training steps to execute (default: varies depending on the
+     * model type)
+     *
+     * For SDXL LoRA training, please use `numTextTrainSteps` and `numUNetTrainSteps`
+     * instead
+     *
+     * Default value varies depending on the model type:
+     *
+     * - For SD1.5: round((number of training images \* 225) / 3)
+     * - For SDXL: number of training images \* 175
+     * - For Flux: number of training images \* 100
+     *
+     * Maximum value varies depending on the model type:
+     *
+     * - For SD1.5 and SDXL: [0, 40000]
+     * - For Flux: [0, 10000]
      */
-    thumbnail?: Model.Thumbnail;
+    maxTrainSteps?: number;
 
     /**
-     * Array of training image pairs
+     * The number of epochs to train for
+     *
+     * Only available for Flux LoRA training
      */
-    trainingImagePairs?: Array<Model.TrainingImagePair>;
+    nbEpochs?: number;
 
     /**
-     * The URLs of the first 3 training images of the model. To retrieve the full set
-     * of images, get it by modelId
+     * The number of times to repeat the training
+     *
+     * Only available for Flux LoRA training
      */
-    trainingImages?: Array<Model.TrainingImage>;
+    nbRepeats?: number;
 
     /**
-     * Additional information about the training progress of the model
+     * The number of training steps for the text encoder
+     *
+     * Only available for SDXL LoRA training
      */
-    trainingProgress?: Model.TrainingProgress;
+    numTextTrainSteps?: number;
 
     /**
-     * Additional information about the model's training
+     * The number of training steps for the UNet
+     *
+     * Only available for SDXL LoRA training
      */
-    trainingStats?: Model.TrainingStats;
+    numUNetTrainSteps?: number;
 
     /**
-     * The UI configuration for the model
+     * Optimize the model training task for a specific type of input images. The
+     * available values are:
+     *
+     * - "likeness": optimize training for likeness or portrait (targets specific
+     *   transformer blocks)
+     * - "all": train all transformer blocks
+     * - "none": train no specific transformer blocks
+     *
+     * This parameter controls which double and single transformer blocks are trained
+     * during the LoRA training process.
+     *
+     * Only available for Flux LoRA training
      */
-    uiConfig?: Model.UiConfig;
+    optimizeFor?: 'likeness';
 
     /**
-     * (Deprecated) The user ID (example: "user_VFhihHKMRZyDDnZAJwLb2Q")
+     * The weight of prior preservation loss
+     *
+     * Only available for SD15 and SDXL LoRA training
      */
-    userId?: string;
-  }
+    priorLossWeight?: number;
 
-  export namespace Model {
     /**
-     * The class of the model
+     * Whether to random crop or center crop images before resizing to the working
+     * resolution
+     *
+     * Only available for SD15 and SDXL LoRA training
      */
-    export interface Class {
-      /**
-       * The category slug of the class (example: "art-style")
-       */
-      category: string;
-
-      /**
-       * The concept prompt of the class (example: "a sks character design")
-       */
-      conceptPrompt: string;
-
-      /**
-       * The model ID of the class (example: "stable-diffusion-v1-5")
-       */
-      modelId: string;
-
-      /**
-       * The class name (example: "Character Design")
-       */
-      name: string;
-
-      /**
-       * The class prompt (example: "a character design")
-       */
-      prompt: string;
-
-      /**
-       * The class slug (example: "art-style-character-design")
-       */
-      slug: string;
-
-      /**
-       * The class status (only published classes are listed, but unpublished classes can
-       * still appear in existing models)
-       */
-      status: 'published' | 'unpublished';
-
-      /**
-       * Some example images URLs to showcase the class
-       */
-      thumbnails: Array<string>;
-    }
-
-    export interface Concept {
-      /**
-       * The model ID (example: "model_eyVcnFJcR92BxBkz7N6g5w")
-       */
-      modelId: string;
-
-      /**
-       * The scale of the model (example: 1.0) For Flux Kontext Prompt Editing, the scale
-       * is between 0 and 2.
-       */
-      scale: number;
-
-      /**
-       * The epoch of the model (example: "000001") Only available for Flux Lora Trained
-       * models
-       */
-      modelEpoch?: string;
-    }
-
-    export interface Epoch {
-      /**
-       * The epoch hash to identify the epoch
-       */
-      epoch: string;
-
-      /**
-       * The assets of the epoch if sample prompts as been supplied during training
-       */
-      assets?: Array<Epoch.Asset>;
-    }
-
-    export namespace Epoch {
-      export interface Asset {
-        /**
-         * The AssetId of the image during training (example:
-         * "asset_GTrL3mq4SXWyMxkOHRxlpw")
-         */
-        assetId: string;
+    randomCrop?: boolean;
 
-        /**
-         * The url of the asset
-         */
-        url: string;
-      }
-    }
+    /**
+     * Ratio of random crops
+     *
+     * Only available for SD15 and SDXL LoRA training
+     */
+    randomCropRatio?: number;
 
     /**
-     * Defines the input parameters for a model. Use this to understand the available
-     * input parameters for a given `modelId` when calling
-     * `POST /generate/custom/{modelId}`. See {@link
-     * https://docs.scenario.com/docs/video-generation} for examples.
+     * Scale of random crops
+     *
+     * Only available for SD15 and SDXL LoRA training
      */
-    export interface Input {
-      /**
-       * The name that must be user to call the model through the API
-       */
-      name: string;
+    randomCropScale?: number;
 
-      /**
-       * The data type of the input
-       */
-      type:
-        | 'boolean'
-        | 'file'
-        | 'file_array'
-        | 'inputs_array'
-        | 'model'
-        | 'model_array'
-        | 'number'
-        | 'number_array'
-        | 'string'
-        | 'string_array';
+    /**
+     * The dimension of the LoRA update matrices
+     *
+     * Only available for SDXL (deprecated), Flux LoRA and Musubi training
+     *
+     * Default value varies depending on the model type:
+     *
+     * - For SDXL (deprecated): 64
+     * - For Flux: 16
+     * - For Musubi: 64
+     *
+     * Each trainer enforces its own tighter limit (Flux LoRA: [2; 64], Musubi: [2;
+     * 128])
+     */
+    rank?: number;
 
-      /**
-       * The allowed values for the input. For \`string\` or \`number\` types, creates a
-       * single-select dropdown. For \`string_array\` type, creates a multi-select
-       * dropdown.
-       */
-      allowedValues?: Array<unknown>;
+    /**
+     * Whether to remove background noise from audio samples before cloning. When
+     * enabled, each sample must be at least 5 seconds long.
+     *
+     * Only available for ElevenLabs voice training
+     */
+    removeBackgroundNoise?: boolean;
 
-      /**
-       * Specifies the background behavior for the input. Only available for \`file\` and
-       * \`file_array\` input types with kind \`image\`.
-       */
-      backgroundBehavior?: 'opaque' | 'transparent';
+    /**
+     * The prompts to use for each epoch Only available for Flux LoRA training
+     */
+    samplePrompts?: Array<string>;
 
-      /**
-       * Whether the input is a color or not. Only available for \`string\` input type.
-       */
-      color?: boolean;
+    /**
+     * The sample prompt images (AssetIds) paired with samplePrompts Only available for
+     * Flux LoRA training Must be the same length as samplePrompts
+     */
+    sampleSourceImages?: Array<string>;
 
-      /**
-       * Whether this input affects the model's cost calculation
-       */
-      costImpact?: boolean;
+    /**
+     * Whether to scale the learning rate
+     *
+     * Note: Legacy parameter, will be ignored
+     *
+     * Only available for SD15 and SDXL LoRA training
+     */
+    scaleLr?: boolean;
 
-      /**
-       * The default value for the input
-       */
-      default?: unknown;
+    /**
+     * Used to reproduce previous results. Default: randomly generated number.
+     *
+     * Only available for SD15 and SDXL LoRA training
+     */
+    seed?: number;
 
-      /**
-       * Help text displayed in the UI to provide additional information about the input
-       */
-      description?: string;
+    /**
+     * Whether to train the text encoder or not
+     *
+     * Example: For 100 steps and a value of 0.2, it means that the text encoder will
+     * be trained for 20 steps and then the UNet for 80 steps
+     *
+     * Note: Legacy parameter, please use `numTextTrainSteps` and `numUNetTrainSteps`
+     *
+     * Only available for SD15 and SDXL LoRA training
+     */
+    textEncoderTrainingRatio?: number;
 
-      /**
-       * Used to visually group inputs together in the UI. Inputs with the same group
-       * value appear consecutively in the UI.
-       */
-      group?: string;
+    /**
+     * Validation frequency. Cannot be greater than maxTrainSteps value
+     *
+     * Only available for SD15 and SDXL LoRA training
+     */
+    validationFrequency?: number;
 
-      /**
-       * Hint text displayed in the UI as a tooltip to guide the user
-       */
-      hint?: string;
+    /**
+     * Validation prompt
+     *
+     * Only available for SD15 and SDXL LoRA training
+     */
+    validationPrompt?: string;
 
-      /**
-       * The list of inputs which form an object within a container array. All inputs are
-       * the same as the current object. This is only available for type inputs_array
-       * inputs.
-       */
-      inputs?: Array<{ [key: string]: unknown }>;
-
-      /**
-       * The asset kind of the input. Only taken into account for \`file\` and
-       * \`file_array\` input types. If model provides multiple kinds, the input will be
-       * not able to create the asset on the flight on API side with dataurl without
-       * data:kind, prefix
-       */
-      kind?: '3d' | 'audio' | 'document' | 'image' | 'image-hdr' | 'json' | 'video';
-
-      /**
-       * The label displayed in the UI for this input
-       */
-      label?: string;
-
-      /**
-       * The name of the file input field to use as the mask source
-       */
-      maskFrom?: string;
-
-      /**
-       * The maximum allowed value. Only available for \`number\` and \`array\` input
-       * types.
-       */
-      max?: number;
-
-      /**
-       * The maximum allowed length for \`string\` inputs. Also applies to each item in
-       * \`string_array\`.
-       */
-      maxLength?: number;
-
-      /**
-       * The maximum allowed file size in bytes. Only applies to \`file\` and
-       * \`file_array\` input types. Validated against \`asset.properties.size\` at job
-       * creation time.
-       */
-      maxSize?: number;
-
-      /**
-       * The minimum allowed value. Only available for \`number\` and array input types.
-       */
-      min?: number;
-
-      /**
-       * The minimum allowed length for string inputs. Also applies to each item in
-       * \`string_array\`.
-       */
-      minLength?: number;
-
-      /**
-       * The allowed model types for this input. Example: \`["flux.1-lora"]\`. Only
-       * available for \`model_array\` input type.
-       */
-      modelTypes?: Array<
-        | 'custom'
-        | 'elevenlabs-voice'
-        | 'flux.1'
-        | 'flux.1-composition'
-        | 'flux.1-kontext-dev'
-        | 'flux.1-kontext-lora'
-        | 'flux.1-krea-dev'
-        | 'flux.1-krea-lora'
-        | 'flux.1-lora'
-        | 'flux.1-pro'
-        | 'flux.1.1-pro-ultra'
-        | 'flux.2-dev-edit-lora'
-        | 'flux.2-dev-lora'
-        | 'flux.2-klein-4b-edit-lora'
-        | 'flux.2-klein-4b-lora'
-        | 'flux.2-klein-9b-edit-lora'
-        | 'flux.2-klein-9b-lora'
-        | 'flux.2-klein-base-4b-edit-lora'
-        | 'flux.2-klein-base-4b-lora'
-        | 'flux.2-klein-base-9b-edit-lora'
-        | 'flux.2-klein-base-9b-lora'
-        | 'flux1.1-pro'
-        | 'gpt-image-1'
-        | 'qwen-image-2512-lora'
-        | 'qwen-image-edit-2509-lora'
-        | 'qwen-image-edit-2511-lora'
-        | 'qwen-image-edit-lora'
-        | 'qwen-image-lora'
-        | 'sd-1_5'
-        | 'sd-1_5-composition'
-        | 'sd-1_5-lora'
-        | 'sd-xl'
-        | 'sd-xl-composition'
-        | 'sd-xl-lora'
-        | 'zimage-de-turbo-lora'
-        | 'zimage-lora'
-        | 'zimage-turbo-lora'
-      >;
-
-      /**
-       * Whether this input represents a parent asset to assign to the produced assets.
-       * Only available for \`file\` and \`file_array\` input types.
-       *
-       * For \`file_array\`, the parent asset is the first item in the array.
-       */
-      parent?: boolean;
-
-      /**
-       * Placeholder text for the input. Only available for 'string' input type.
-       */
-      placeholder?: string;
-
-      /**
-       * Whether the input is a prompt. When true, displays as a text area with prompt
-       * spark feature. Only available for \`string\` input type.
-       */
-      prompt?: boolean;
-
-      /**
-       * Whether the input is used with prompt spark. Only available for \`string\` input
-       * type.
-       */
-      promptSpark?: boolean;
-
-      /**
-       * Set of rules that describes when this input is required:
-       *
-       * - \`always\`: Input is always required
-       * - \`ifNotDefined\`: Input is required when another specified input is not
-       *   defined
-       * - \`ifDefined\`: Input is required when another specified input is defined
-       * - \`conditionalValues\`: Input is required when another input has a specific
-       *   value
-       *
-       * By default, the input is not required.
-       */
-      required?: Input.Required;
-
-      /**
-       * The step increment for numeric inputs. Only available for \`number\` input type.
-       */
-      step?: number;
-    }
-
-    export namespace Input {
-      /**
-       * Set of rules that describes when this input is required:
-       *
-       * - \`always\`: Input is always required
-       * - \`ifNotDefined\`: Input is required when another specified input is not
-       *   defined
-       * - \`ifDefined\`: Input is required when another specified input is defined
-       * - \`conditionalValues\`: Input is required when another input has a specific
-       *   value
-       *
-       * By default, the input is not required.
-       */
-      export interface Required {
-        /**
-         * Whether the input is always required
-         */
-        always?: boolean;
-
-        /**
-         * Makes this input required when another input has a specific value:
-         *
-         * - Key: name of the input to check
-         * - Value: operation and allowed values that trigger the requirement
-         */
-        conditionalValues?: unknown;
-
-        /**
-         * Makes this input required when another input is defined:
-         *
-         * - Key: name of the input that must be defined
-         * - Value: message to display when this input is required
-         */
-        ifDefined?: unknown;
-
-        /**
-         * Makes this input required when another input is not defined:
-         *
-         * - Key: name of the input that must be undefined
-         * - Value: message to display when this input is required
-         */
-        ifNotDefined?: unknown;
-      }
-    }
-
-    /**
-     * The parameters of the model
-     */
-    export interface Parameters {
-      /**
-       * Age group of the voice (for professional cloning)
-       *
-       * Only available for ElevenLabs voice training
-       */
-      age?: string;
-
-      /**
-       * The batch size Less steps, and will increase the learning rate
-       *
-       * Only available for Flux LoRA training
-       */
-      batchSize?: number;
-
-      /**
-       * The prompt to specify images in the same class as provided instance images
-       *
-       * Only available for SD15 training
-       */
-      classPrompt?: string;
-
-      /**
-       * Type of voice cloning: "instant" (fast) or "professional" (higher quality,
-       * requires captcha)
-       *
-       * Only available for ElevenLabs voice training
-       */
-      cloneType?: string;
-
-      /**
-       * The prompt with identifier specifying the instance (or subject) of the class
-       * (example: "a daiton dog")
-       *
-       * Default value varies depending on the model type:
-       *
-       * - For SD1.5: "daiton" if no class is associated with the model
-       * - For SDXL: "daiton"
-       * - For Flux: ""
-       */
-      conceptPrompt?: string;
-
-      /**
-       * Gender of the voice (for professional cloning)
-       *
-       * Only available for ElevenLabs voice training
-       */
-      gender?: string;
-
-      /**
-       * Language of the audio samples (ISO 639-1 code)
-       *
-       * Only available for ElevenLabs voice training
-       */
-      language?: string;
-
-      /**
-       * Initial learning rate (after the potential warmup period)
-       *
-       * Default value varies depending on the model type:
-       *
-       * - For SD1.5 and SDXL: 0.000005
-       * - For Flux: 0.0001
-       */
-      learningRate?: number;
-
-      /**
-       * Initial learning rate (after the potential warmup period) for the text encoder
-       *
-       * Maximum [Flux LoRA: 0.001] Default [SDXL: 0.00005 | Flux LoRA: 0.00001] Minimum
-       * [SDXL: 0 | Flux LoRA: 0.000001]
-       */
-      learningRateTextEncoder?: number;
-
-      /**
-       * Initial learning rate (after the potential warmup period) for the UNet
-       *
-       * Only available for SDXL LoRA training
-       */
-      learningRateUnet?: number;
-
-      /**
-       * The scheduler type to use (default: "constant")
-       *
-       * Only available for SD15 and SDXL LoRA training
-       */
-      lrScheduler?:
-        | 'constant'
-        | 'constant-with-warmup'
-        | 'cosine'
-        | 'cosine-with-restarts'
-        | 'linear'
-        | 'polynomial';
-
-      /**
-       * Maximum number of training steps to execute (default: varies depending on the
-       * model type)
-       *
-       * For SDXL LoRA training, please use `numTextTrainSteps` and `numUNetTrainSteps`
-       * instead
-       *
-       * Default value varies depending on the model type:
-       *
-       * - For SD1.5: round((number of training images \* 225) / 3)
-       * - For SDXL: number of training images \* 175
-       * - For Flux: number of training images \* 100
-       *
-       * Maximum value varies depending on the model type:
-       *
-       * - For SD1.5 and SDXL: [0, 40000]
-       * - For Flux: [0, 10000]
-       */
-      maxTrainSteps?: number;
-
-      /**
-       * The number of epochs to train for
-       *
-       * Only available for Flux LoRA training
-       */
-      nbEpochs?: number;
-
-      /**
-       * The number of times to repeat the training
-       *
-       * Only available for Flux LoRA training
-       */
-      nbRepeats?: number;
-
-      /**
-       * The number of training steps for the text encoder
-       *
-       * Only available for SDXL LoRA training
-       */
-      numTextTrainSteps?: number;
-
-      /**
-       * The number of training steps for the UNet
-       *
-       * Only available for SDXL LoRA training
-       */
-      numUNetTrainSteps?: number;
-
-      /**
-       * Optimize the model training task for a specific type of input images. The
-       * available values are:
-       *
-       * - "likeness": optimize training for likeness or portrait (targets specific
-       *   transformer blocks)
-       * - "all": train all transformer blocks
-       * - "none": train no specific transformer blocks
-       *
-       * This parameter controls which double and single transformer blocks are trained
-       * during the LoRA training process.
-       *
-       * Only available for Flux LoRA training
-       */
-      optimizeFor?: 'likeness';
-
-      /**
-       * The weight of prior preservation loss
-       *
-       * Only available for SD15 and SDXL LoRA training
-       */
-      priorLossWeight?: number;
-
-      /**
-       * Whether to random crop or center crop images before resizing to the working
-       * resolution
-       *
-       * Only available for SD15 and SDXL LoRA training
-       */
-      randomCrop?: boolean;
-
-      /**
-       * Ratio of random crops
-       *
-       * Only available for SD15 and SDXL LoRA training
-       */
-      randomCropRatio?: number;
-
-      /**
-       * Scale of random crops
-       *
-       * Only available for SD15 and SDXL LoRA training
-       */
-      randomCropScale?: number;
-
-      /**
-       * The dimension of the LoRA update matrices
-       *
-       * Only available for SDXL (deprecated), Flux LoRA and Musubi training
-       *
-       * Default value varies depending on the model type:
-       *
-       * - For SDXL (deprecated): 64
-       * - For Flux: 16
-       * - For Musubi: 64
-       *
-       * Each trainer enforces its own tighter limit (Flux LoRA: [2; 64], Musubi: [2;
-       * 128])
-       */
-      rank?: number;
-
-      /**
-       * Whether to remove background noise from audio samples before cloning. When
-       * enabled, each sample must be at least 5 seconds long.
-       *
-       * Only available for ElevenLabs voice training
-       */
-      removeBackgroundNoise?: boolean;
-
-      /**
-       * The prompts to use for each epoch Only available for Flux LoRA training
-       */
-      samplePrompts?: Array<string>;
-
-      /**
-       * The sample prompt images (AssetIds) paired with samplePrompts Only available for
-       * Flux LoRA training Must be the same length as samplePrompts
-       */
-      sampleSourceImages?: Array<string>;
-
-      /**
-       * Whether to scale the learning rate
-       *
-       * Note: Legacy parameter, will be ignored
-       *
-       * Only available for SD15 and SDXL LoRA training
-       */
-      scaleLr?: boolean;
-
-      /**
-       * Used to reproduce previous results. Default: randomly generated number.
-       *
-       * Only available for SD15 and SDXL LoRA training
-       */
-      seed?: number;
-
-      /**
-       * Whether to train the text encoder or not
-       *
-       * Example: For 100 steps and a value of 0.2, it means that the text encoder will
-       * be trained for 20 steps and then the UNet for 80 steps
-       *
-       * Note: Legacy parameter, please use `numTextTrainSteps` and `numUNetTrainSteps`
-       *
-       * Only available for SD15 and SDXL LoRA training
-       */
-      textEncoderTrainingRatio?: number;
-
-      /**
-       * Validation frequency. Cannot be greater than maxTrainSteps value
-       *
-       * Only available for SD15 and SDXL LoRA training
-       */
-      validationFrequency?: number;
-
-      /**
-       * Validation prompt
-       *
-       * Only available for SD15 and SDXL LoRA training
-       */
-      validationPrompt?: string;
-
-      /**
-       * Description of the voice characteristics
-       *
-       * Only available for ElevenLabs voice training
-       */
-      voiceDescription?: string;
-
-      /**
-       * The Weights And Bias key to use for logging. The maximum length is 40 characters
-       */
-      wandbKey?: string;
-    }
-
-    /**
-     * Aggregated performance stats
-     */
-    export interface PerformanceStats {
-      /**
-       * Performance metrics per variant
-       */
-      variants: Array<PerformanceStats.Variant>;
-
-      /**
-       * Default variant key for quick model comparison
-       */
-      default?: string;
-    }
-
-    export namespace PerformanceStats {
-      /**
-       * Performance stats for a model variant
-       */
-      export interface Variant {
-        /**
-         * The generation capability (example: "txt2img", "img2video", "txt2audio")
-         */
-        capability: string;
-
-        /**
-         * When these stats were last computed (ISO date)
-         */
-        computedAt: string;
-
-        /**
-         * Unique variant identifier (example: "txt2img:1K", "img2video:2K", "txt2audio")
-         */
-        variantKey: string;
-
-        /**
-         * External quality score from arena.ai leaderboard
-         */
-        arenaScore?: Variant.ArenaScore;
-
-        /**
-         * Maximum cost per output asset (CU)
-         */
-        costPerAssetMaxCU?: number;
-
-        /**
-         * Minimum cost per output asset (CU)
-         */
-        costPerAssetMinCU?: number;
-
-        /**
-         * Median cost per output asset (CU)
-         */
-        costPerAssetP50CU?: number;
-
-        /**
-         * Inference latency P50 per output asset (seconds)
-         */
-        inferenceLatencyP50Sec?: number;
-
-        /**
-         * Inference latency P75 per output asset (seconds)
-         */
-        inferenceLatencyP75Sec?: number;
-
-        /**
-         * The resolution bucket (example: "0.5K", "1K", "2K", "4K")
-         */
-        resolution?: string;
-
-        /**
-         * Total latency P50 per output asset, including queue time (seconds)
-         */
-        totalLatencyP50Sec?: number;
-
-        /**
-         * Total latency P75 per output asset, including queue time (seconds)
-         */
-        totalLatencyP75Sec?: number;
-      }
-
-      export namespace Variant {
-        /**
-         * External quality score from arena.ai leaderboard
-         */
-        export interface ArenaScore {
-          /**
-           * Arena category (example: "text_to_image", "image_to_video")
-           */
-          arenaCategory: string;
-
-          /**
-           * Model name on arena.ai
-           */
-          arenaModelName: string;
-
-          /**
-           * When this score was last fetched (ISO date)
-           */
-          fetchedAt: string;
-
-          /**
-           * Rank in the arena category
-           */
-          rank: number;
-
-          /**
-           * ELO rating
-           */
-          rating: number;
-
-          /**
-           * ELO rating confidence interval lower bound
-           */
-          ratingLower: number;
-
-          /**
-           * ELO rating confidence interval upper bound
-           */
-          ratingUpper: number;
-
-          /**
-           * Number of human votes
-           */
-          votes: number;
-        }
-      }
-    }
-
-    /**
-     * A thumbnail for your model
-     */
-    export interface Thumbnail {
-      /**
-       * The AssetId of the image used as a thumbnail for your model (example:
-       * "asset_GTrL3mq4SXWyMxkOHRxlpw")
-       */
-      assetId: string;
-
-      /**
-       * The url of the image used as a thumbnail for your model
-       */
-      url: string;
-    }
-
-    export interface TrainingImagePair {
-      /**
-       * The instruction for the image pair, source to target
-       */
-      instruction?: string;
-
-      /**
-       * The source asset ID (must be a training asset)
-       */
-      sourceId?: string;
-
-      /**
-       * The target asset ID (must be a training asset)
-       */
-      targetId?: string;
-    }
-
-    export interface TrainingImage {
-      /**
-       * The training image ID (example: "asset_GTrL3mq4SXWyMxkOHRxlpw")
-       */
-      id: string;
-
-      /**
-       * Automatic captioning of the image
-       */
-      automaticCaptioning: string;
-
-      /**
-       * The training image upload date as an ISO string (example:
-       * "2023-02-03T11:19:41.579Z")
-       */
-      createdAt: string;
-
-      /**
-       * Description for the image
-       */
-      description: string;
-
-      /**
-       * The URL of the image
-       */
-      downloadUrl: string;
-
-      /**
-       * The original file name of the image (example: "my-training-image.jpg")
-       */
-      name: string;
-    }
+    /**
+     * Description of the voice characteristics
+     *
+     * Only available for ElevenLabs voice training
+     */
+    voiceDescription?: string;
 
     /**
-     * Additional information about the training progress of the model
+     * The Weights And Bias key to use for logging. The maximum length is 40 characters
      */
-    export interface TrainingProgress {
-      /**
-       * The stage of the request
-       */
-      stage: 'pending' | 'pending-captcha' | 'queued-for-train' | 'running-train' | 'starting-train';
-
-      /**
-       * Timestamp in milliseconds of the last time the training progress was updated
-       */
-      updatedAt: number;
+    wandbKey?: string;
+  }
 
-      /**
-       * Position of the job in the queue (ie. the number of job in the queue before this
-       * one)
-       */
-      position?: number;
+  /**
+   * Aggregated performance stats
+   */
+  export interface PerformanceStats {
+    /**
+     * Performance metrics per variant
+     */
+    variants: Array<PerformanceStats.Variant>;
 
-      /**
-       * The progress of the job
-       */
-      progress?: number;
+    /**
+     * Default variant key for quick model comparison
+     */
+    default?: string;
+  }
 
+  export namespace PerformanceStats {
+    /**
+     * Performance stats for a model variant
+     */
+    export interface Variant {
       /**
-       * The remaining time in milliseconds
+       * The generation capability (example: "txt2img", "img2video", "txt2audio")
        */
-      remainingTimeMs?: number;
+      capability: string;
 
       /**
-       * The timestamp in millisecond marking the start of the process
+       * When these stats were last computed (ISO date)
        */
-      startedAt?: number;
-    }
+      computedAt: string;
 
-    /**
-     * Additional information about the model's training
-     */
-    export interface TrainingStats {
       /**
-       * The training end time as an ISO date string
+       * Unique variant identifier (example: "txt2img:1K", "img2video:2K", "txt2audio")
        */
-      endedAt?: string;
+      variantKey: string;
 
       /**
-       * The training queued duration in seconds
+       * External quality score from arena.ai leaderboard
        */
-      queueDuration?: number;
+      arenaScore?: Variant.ArenaScore;
 
       /**
-       * The training start time as an ISO date string
+       * Maximum cost per output asset (CU)
        */
-      startedAt?: string;
+      costPerAssetMaxCU?: number;
 
       /**
-       * The training duration in seconds
+       * Minimum cost per output asset (CU)
        */
-      trainDuration?: number;
-    }
+      costPerAssetMinCU?: number;
 
-    /**
-     * The UI configuration for the model
-     */
-    export interface UiConfig {
       /**
-       * Configuration for the input properties
+       * Median cost per output asset (CU)
        */
-      inputProperties?: { [key: string]: UiConfig.InputProperties };
+      costPerAssetP50CU?: number;
 
       /**
-       * Configuration for the loras component
+       * Inference latency P50 per output asset (seconds)
        */
-      lorasComponent?: UiConfig.LorasComponent;
+      inferenceLatencyP50Sec?: number;
 
       /**
-       * Configuration for the presets
+       * Inference latency P75 per output asset (seconds)
        */
-      presets?: Array<UiConfig.Preset>;
+      inferenceLatencyP75Sec?: number;
 
       /**
-       * Configuration for the resolution component
+       * The resolution bucket (example: "0.5K", "1K", "2K", "4K")
        */
-      resolutionComponent?: UiConfig.ResolutionComponent;
+      resolution?: string;
 
       /**
-       * Configuration for the selects
+       * Total latency P50 per output asset, including queue time (seconds)
        */
-      selects?: { [key: string]: unknown };
+      totalLatencyP50Sec?: number;
 
       /**
-       * Configuration for the trigger generate button
+       * Total latency P75 per output asset, including queue time (seconds)
        */
-      triggerGenerate?: UiConfig.TriggerGenerate;
+      totalLatencyP75Sec?: number;
     }
 
-    export namespace UiConfig {
-      export interface InputProperties {
-        collapsed?: boolean;
-      }
-
+    export namespace Variant {
       /**
-       * Configuration for the loras component
+       * External quality score from arena.ai leaderboard
        */
-      export interface LorasComponent {
+      export interface ArenaScore {
         /**
-         * The label of the component
+         * Arena category (example: "text_to_image", "image_to_video")
          */
-        label: string;
+        arenaCategory: string;
 
         /**
-         * The input name of the model (model_array)
+         * Model name on arena.ai
          */
-        modelInput: string;
+        arenaModelName: string;
 
         /**
-         * The input name of the scale (number_array)
+         * When this score was last fetched (ISO date)
          */
-        scaleInput: string;
+        fetchedAt: string;
 
         /**
-         * The input model id (example: a composition or a single LoRA modelId) If
-         * specified, the model id will be attached to the output asset as a metadata If
-         * the model-decomposer parser is specified on it, modelInput and scaleInput will
-         * be automatically populated
+         * Rank in the arena category
          */
-        modelIdInput?: string;
-      }
+        rank: number;
 
-      export interface Preset {
-        fields: Array<string>;
-
-        presets: unknown;
-      }
-
-      /**
-       * Configuration for the resolution component
-       */
-      export interface ResolutionComponent {
         /**
-         * The input name of the height
+         * ELO rating
          */
-        heightInput: string;
+        rating: number;
 
         /**
-         * The label of the component
+         * ELO rating confidence interval lower bound
          */
-        label: string;
+        ratingLower: number;
 
         /**
-         * The resolution presets
+         * ELO rating confidence interval upper bound
          */
-        presets: Array<ResolutionComponent.Preset>;
+        ratingUpper: number;
 
         /**
-         * The input name of the width
+         * Number of human votes
          */
-        widthInput: string;
+        votes: number;
       }
+    }
+  }
 
-      export namespace ResolutionComponent {
-        export interface Preset {
-          height: number;
+  /**
+   * A thumbnail for your model
+   */
+  export interface Thumbnail {
+    /**
+     * The AssetId of the image used as a thumbnail for your model (example:
+     * "asset_GTrL3mq4SXWyMxkOHRxlpw")
+     */
+    assetId: string;
 
-          label: string;
+    /**
+     * The url of the image used as a thumbnail for your model
+     */
+    url: string;
+  }
 
-          width: number;
-        }
-      }
+  export interface TrainingImagePair {
+    /**
+     * The instruction for the image pair, source to target
+     */
+    instruction?: string;
+
+    /**
+     * The source asset ID (must be a training asset)
+     */
+    sourceId?: string;
+
+    /**
+     * The target asset ID (must be a training asset)
+     */
+    targetId?: string;
+  }
+
+  export interface TrainingImage {
+    /**
+     * The training image ID (example: "asset_GTrL3mq4SXWyMxkOHRxlpw")
+     */
+    id: string;
+
+    /**
+     * Automatic captioning of the image
+     */
+    automaticCaptioning: string;
+
+    /**
+     * The training image upload date as an ISO string (example:
+     * "2023-02-03T11:19:41.579Z")
+     */
+    createdAt: string;
+
+    /**
+     * Description for the image
+     */
+    description: string;
+
+    /**
+     * The URL of the image
+     */
+    downloadUrl: string;
+
+    /**
+     * The original file name of the image (example: "my-training-image.jpg")
+     */
+    name: string;
+  }
+
+  /**
+   * Additional information about the training progress of the model
+   */
+  export interface TrainingProgress {
+    /**
+     * The stage of the request
+     */
+    stage: 'pending' | 'pending-captcha' | 'queued-for-train' | 'running-train' | 'starting-train';
+
+    /**
+     * Timestamp in milliseconds of the last time the training progress was updated
+     */
+    updatedAt: number;
+
+    /**
+     * Position of the job in the queue (ie. the number of job in the queue before this
+     * one)
+     */
+    position?: number;
+
+    /**
+     * The progress of the job
+     */
+    progress?: number;
+
+    /**
+     * The remaining time in milliseconds
+     */
+    remainingTimeMs?: number;
+
+    /**
+     * The timestamp in millisecond marking the start of the process
+     */
+    startedAt?: number;
+  }
+
+  /**
+   * Additional information about the model's training
+   */
+  export interface TrainingStats {
+    /**
+     * The training end time as an ISO date string
+     */
+    endedAt?: string;
+
+    /**
+     * The training queued duration in seconds
+     */
+    queueDuration?: number;
+
+    /**
+     * The training start time as an ISO date string
+     */
+    startedAt?: string;
+
+    /**
+     * The training duration in seconds
+     */
+    trainDuration?: number;
+  }
+
+  /**
+   * The UI configuration for the model
+   */
+  export interface UiConfig {
+    /**
+     * Configuration for the input properties
+     */
+    inputProperties?: { [key: string]: UiConfig.InputProperties };
+
+    /**
+     * Configuration for the loras component
+     */
+    lorasComponent?: UiConfig.LorasComponent;
+
+    /**
+     * Configuration for the presets
+     */
+    presets?: Array<UiConfig.Preset>;
+
+    /**
+     * Configuration for the resolution component
+     */
+    resolutionComponent?: UiConfig.ResolutionComponent;
+
+    /**
+     * Configuration for the selects
+     */
+    selects?: { [key: string]: unknown };
+
+    /**
+     * Configuration for the trigger generate button
+     */
+    triggerGenerate?: UiConfig.TriggerGenerate;
+  }
+
+  export namespace UiConfig {
+    export interface InputProperties {
+      collapsed?: boolean;
+    }
 
+    /**
+     * Configuration for the loras component
+     */
+    export interface LorasComponent {
       /**
-       * Configuration for the trigger generate button
+       * The label of the component
        */
-      export interface TriggerGenerate {
-        label: string;
+      label: string;
 
-        /**
-         * The 'name' of the input where the trigger generate button will be displayed
-         * (after the input). Do not specify both position and after.
-         */
-        after?: string;
+      /**
+       * The input name of the model (model_array)
+       */
+      modelInput: string;
 
-        /**
-         * The position of the trigger generate button. If position specified, the button
-         * will be displayed at the specified position. Do not specify both position and
-         * after.
-         */
-        position?: 'bottom' | 'top';
+      /**
+       * The input name of the scale (number_array)
+       */
+      scaleInput: string;
+
+      /**
+       * The input model id (example: a composition or a single LoRA modelId) If
+       * specified, the model id will be attached to the output asset as a metadata If
+       * the model-decomposer parser is specified on it, modelInput and scaleInput will
+       * be automatically populated
+       */
+      modelIdInput?: string;
+    }
+
+    export interface Preset {
+      fields: Array<string>;
+
+      presets: unknown;
+    }
+
+    /**
+     * Configuration for the resolution component
+     */
+    export interface ResolutionComponent {
+      /**
+       * The input name of the height
+       */
+      heightInput: string;
+
+      /**
+       * The label of the component
+       */
+      label: string;
+
+      /**
+       * The resolution presets
+       */
+      presets: Array<ResolutionComponent.Preset>;
+
+      /**
+       * The input name of the width
+       */
+      widthInput: string;
+    }
+
+    export namespace ResolutionComponent {
+      export interface Preset {
+        height: number;
+
+        label: string;
+
+        width: number;
       }
     }
+
+    /**
+     * Configuration for the trigger generate button
+     */
+    export interface TriggerGenerate {
+      label: string;
+
+      /**
+       * The 'name' of the input where the trigger generate button will be displayed
+       * (after the input). Do not specify both position and after.
+       */
+      after?: string;
+
+      /**
+       * The position of the trigger generate button. If position specified, the button
+       * will be displayed at the specified position. Do not specify both position and
+       * after.
+       */
+      position?: 'bottom' | 'top';
+    }
   }
 }
 
@@ -5372,6 +5372,7 @@ export namespace ModelCopyResponse {
     capabilities: Array<
       | '3d23d'
       | 'audio2audio'
+      | 'audio2video'
       | 'controlnet'
       | 'controlnet_img2img'
       | 'controlnet_inpaint'
@@ -5398,6 +5399,7 @@ export namespace ModelCopyResponse {
       | 'txt2txt'
       | 'txt2video'
       | 'video23d'
+      | 'video2audio'
       | 'video2img'
       | 'video2video'
     >;
@@ -6735,6 +6737,7 @@ export namespace ModelGetBulkResponse {
     capabilities?: Array<
       | '3d23d'
       | 'audio2audio'
+      | 'audio2video'
       | 'controlnet'
       | 'controlnet_img2img'
       | 'controlnet_inpaint'
@@ -6761,6 +6764,7 @@ export namespace ModelGetBulkResponse {
       | 'txt2txt'
       | 'txt2video'
       | 'video23d'
+      | 'video2audio'
       | 'video2img'
       | 'video2video'
     >;
@@ -7973,6 +7977,7 @@ export namespace ModelTransferResponse {
     capabilities: Array<
       | '3d23d'
       | 'audio2audio'
+      | 'audio2video'
       | 'controlnet'
       | 'controlnet_img2img'
       | 'controlnet_inpaint'
@@ -7999,6 +8004,7 @@ export namespace ModelTransferResponse {
       | 'txt2txt'
       | 'txt2video'
       | 'video23d'
+      | 'video2audio'
       | 'video2img'
       | 'video2video'
     >;
@@ -9804,7 +9810,7 @@ export namespace ModelUpdateParams {
   }
 }
 
-export interface ModelListParams {
+export interface ModelListParams extends ModelsCursorParams {
   /**
    * If set to true, returns the full list of models (including blacklisted models)
    * (only available for team admins)
@@ -9853,11 +9859,6 @@ export interface ModelListParams {
    */
   pageSize?: number;
 
-  /**
-   * A token you received in a previous request to query the next page of items
-   */
-  paginationToken?: string;
-
   /**
    * The privacy of the models to return. The default value is `private`, possible
    * values are `private` and `public`
@@ -10106,6 +10107,7 @@ export declare namespace Models {
     type ModelGetBulkResponse as ModelGetBulkResponse,
     type ModelTransferResponse as ModelTransferResponse,
     type ModelUpdateTagsResponse as ModelUpdateTagsResponse,
+    type ModelListResponsesModelsCursor as ModelListResponsesModelsCursor,
     type ModelCreateParams as ModelCreateParams,
     type ModelRetrieveParams as ModelRetrieveParams,
     type ModelUpdateParams as ModelUpdateParams,