File size: 10,767 Bytes
f56a29b | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 | /**
* Media (Image & Video) Generation Provider Type Definitions
*
* Unified types for image generation and video generation
* with extensible architecture to support multiple providers.
*
* Currently Supported Image Providers:
* - Seedream (ByteDance SDXL-based image generation)
* - OpenAI Image (GPT Image API)
* - Qwen Image (Alibaba Cloud Wanx image generation)
* - Nano Banana (Lightweight image generation via Banana.dev)
*
* Currently Supported Video Providers (Phase 2):
* - Seedance (ByteDance video generation)
* - Kling (Kuaishou video generation)
* - Veo (Google DeepMind video generation)
* - Sora (OpenAI video generation)
*
* HOW TO ADD A NEW PROVIDER:
*
* Step 1: Add provider ID to the union type
* - For Image: Add to ImageProviderId below
* - For Video: Add to VideoProviderId below
*
* Step 2: Add provider configuration to constants.ts
* - Define provider metadata (name, icon, aspect ratios, styles, etc.)
* - Add to IMAGE_PROVIDERS or VIDEO_PROVIDERS registry
*
* Step 3: Implement provider logic in image-providers.ts or video-providers.ts
* - Add case to generateImage() or generateVideo() switch statement
* - Implement API call logic for the new provider
* - For async task-based providers, implement MediaTaskAdapter
*
* Step 4: Add i18n translations
* - Add provider name translations in lib/i18n.ts
* - Format: `provider{ProviderName}Image` or `provider{ProviderName}Video`
*
* Step 5 (Optional): Add provider-specific options
* - Extend ImageGenerationOptions or VideoGenerationOptions as needed
* - Document provider-specific parameters in JSDoc
*
* Example: Adding DALL-E Image Provider
* =======================================
* 1. Add 'dall-e' to ImageProviderId union type
* 2. In constants.ts:
* IMAGE_PROVIDERS['dall-e'] = {
* id: 'dall-e',
* name: 'DALL-E',
* requiresApiKey: true,
* defaultBaseUrl: 'https://api.openai.com/v1',
* icon: '/openai.svg',
* supportedAspectRatios: ['1:1', '16:9', '9:16'],
* supportedStyles: ['natural', 'vivid'],
* maxResolution: { width: 1024, height: 1024 }
* }
* 3. In image-providers.ts:
* case 'dall-e':
* return await generateDallEImage(config, options);
* 4. In i18n.ts:
* providerDallEImage: 'DALL-E' / 'DALL-E 图像生成'
*/
// ============================================================================
// Image Generation Types
// ============================================================================
/**
* Image Provider IDs
*
* Add new image providers here as union members.
* Keep in sync with IMAGE_PROVIDERS registry in constants.ts
*/
export type ImageProviderId =
| 'seedream'
| 'openai-image'
| 'qwen-image'
| 'nano-banana'
| 'minimax-image'
| 'grok-image';
// Add new image providers below (uncomment and modify):
// | 'dall-e'
// | 'midjourney'
// | 'stable-diffusion'
/**
* Image Provider Configuration
*
* Describes the capabilities and metadata of an image generation provider.
* Used to populate UI controls and validate generation requests.
*/
/** Model metadata for an image generation model */
export interface ImageModelInfo {
/** Model identifier passed to the API */
id: string;
/** Human-readable display name */
name: string;
}
export interface ImageProviderConfig {
/** Unique provider identifier */
id: ImageProviderId;
/** Human-readable provider name */
name: string;
/** Whether the provider requires an API key for authentication */
requiresApiKey: boolean;
/** Default API base URL (can be overridden in user settings) */
defaultBaseUrl?: string;
/** Path to provider icon asset */
icon?: string;
/** Available models for this provider */
models: ImageModelInfo[];
/** Aspect ratios supported by this provider */
supportedAspectRatios: Array<'16:9' | '4:3' | '1:1' | '9:16'>;
/** Optional artistic styles supported by this provider */
supportedStyles?: string[];
/** Maximum supported output resolution */
maxResolution?: {
width: number;
height: number;
};
}
/**
* Image Generation Configuration
*
* Runtime configuration for making image generation API calls.
* Combines provider selection with authentication credentials.
*/
export interface ImageGenerationConfig {
/** Which image provider to use */
providerId: ImageProviderId;
/** API key for authentication */
apiKey: string;
/** Optional override for the provider's base URL */
baseUrl?: string;
/** Optional model ID override (uses provider default if omitted) */
model?: string;
}
/**
* Image Generation Options
*
* Parameters for a single image generation request.
* Passed alongside ImageGenerationConfig to the provider.
*/
export interface ImageGenerationOptions {
/** Text prompt describing the desired image */
prompt: string;
/** Optional negative prompt to exclude undesired elements */
negativePrompt?: string;
/** Desired output width in pixels */
width?: number;
/** Desired output height in pixels */
height?: number;
/** Desired aspect ratio (provider will calculate dimensions if width/height not set) */
aspectRatio?: '16:9' | '4:3' | '1:1' | '9:16';
/** Optional artistic style (must be supported by the chosen provider) */
style?: string;
}
/**
* Image Generation Result
*
* The output of a successful image generation request.
* Contains either a URL or base64-encoded image data (or both).
*/
export interface ImageGenerationResult {
/** URL to the generated image (if hosted by the provider) */
url?: string;
/** Base64-encoded image data (if returned inline) */
base64?: string;
/** Width of the generated image in pixels */
width: number;
/** Height of the generated image in pixels */
height: number;
}
// ============================================================================
// Video Generation Types (Phase 2)
// ============================================================================
/**
* Video Provider IDs
*
* Add new video providers here as union members.
* Keep in sync with VIDEO_PROVIDERS registry in constants.ts
*/
export type VideoProviderId =
| 'seedance'
| 'kling'
| 'veo'
| 'sora'
| 'minimax-video'
| 'grok-video';
// Add new video providers below (uncomment and modify):
// | 'runway'
// | 'pika'
/**
* Video Provider Configuration
*
* Describes the capabilities and metadata of a video generation provider.
* Used to populate UI controls and validate generation requests.
*/
/** Model metadata for a video generation model (same shape as image) */
export type VideoModelInfo = ImageModelInfo;
export interface VideoProviderConfig {
/** Unique provider identifier */
id: VideoProviderId;
/** Human-readable provider name */
name: string;
/** Whether the provider requires an API key for authentication */
requiresApiKey: boolean;
/** Default API base URL (can be overridden in user settings) */
defaultBaseUrl?: string;
/** Path to provider icon asset */
icon?: string;
/** Available models for this provider */
models: VideoModelInfo[];
/** Aspect ratios supported by this provider */
supportedAspectRatios: Array<'16:9' | '4:3' | '1:1' | '9:16' | '3:4' | '21:9'>;
/** Supported video durations in seconds */
supportedDurations?: number[];
/** Supported output resolutions */
supportedResolutions?: Array<'480p' | '720p' | '1080p'>;
/** Maximum video duration in seconds */
maxDuration?: number;
}
/**
* Video Generation Configuration
*
* Runtime configuration for making video generation API calls.
* Combines provider selection with authentication credentials.
*/
export interface VideoGenerationConfig {
/** Which video provider to use */
providerId: VideoProviderId;
/** API key for authentication */
apiKey: string;
/** Optional override for the provider's base URL */
baseUrl?: string;
/** Optional model ID override (uses provider default if omitted) */
model?: string;
}
/**
* Video Generation Options
*
* Parameters for a single video generation request.
* Passed alongside VideoGenerationConfig to the provider.
*/
export interface VideoGenerationOptions {
/** Text prompt describing the desired video */
prompt: string;
/** Desired video duration in seconds */
duration?: number;
/** Desired aspect ratio */
aspectRatio?: '16:9' | '4:3' | '1:1' | '9:16' | '3:4' | '21:9';
/** Desired output resolution */
resolution?: '480p' | '720p' | '1080p';
}
/**
* Video Generation Result
*
* The output of a successful video generation request.
* Contains the URL to the generated video along with metadata.
*/
export interface VideoGenerationResult {
/** URL to the generated video */
url: string;
/** Duration of the generated video in seconds */
duration: number;
/** Width of the generated video in pixels */
width: number;
/** Height of the generated video in pixels */
height: number;
/** Optional URL to a poster/thumbnail image for the video */
poster?: string;
}
// ============================================================================
// Shared / Cross-cutting Types
// ============================================================================
/**
* Media Generation Request
*
* A unified request type used by the whiteboard/canvas to request
* media generation. Maps to either image or video generation internally.
*/
export interface MediaGenerationRequest {
/** Type of media to generate */
type: 'image' | 'video';
/** Text prompt describing the desired media */
prompt: string;
/** Identifier for the target element on the canvas (e.g. "gen_img_1") */
elementId: string;
/** Desired aspect ratio */
aspectRatio?: '16:9' | '4:3' | '1:1' | '9:16';
/** Optional artistic style hint */
style?: string;
}
/**
* Media Task Adapter
*
* Generic interface for providers that use an asynchronous task pattern
* (submit task, then poll for completion). Many image/video generation
* APIs are async — this adapter abstracts that pattern.
*
* @template TOptions - The generation options type (e.g. ImageGenerationOptions)
* @template TResult - The generation result type (e.g. ImageGenerationResult)
*/
export interface MediaTaskAdapter<TOptions, TResult> {
/**
* Submit a generation task to the provider.
*
* @param options - Generation options for the task
* @returns A task ID that can be used to poll for status
*/
submitTask(options: TOptions): Promise<string>;
/**
* Poll the status of a previously submitted task.
*
* @param taskId - The task ID returned by submitTask()
* @returns The generation result if complete, or null if still processing
*/
pollTaskStatus(taskId: string): Promise<TResult | null>;
}
|