@ai-sdk/prodia 1.0.7 → 1.0.9

package/CHANGELOG.md

@@ -1,5 +1,18 @@
 # @ai-sdk/prodia
 
+## 1.0.9
+
+### Patch Changes
+
+- 3988c08: docs: fix incorrect and outdated provider docs
+
+## 1.0.8
+
+### Patch Changes
+
+- Updated dependencies [462ad00]
+  - @ai-sdk/provider-utils@4.0.10
+
 ## 1.0.7
 
 ### Patch Changes

package/dist/index.js

@@ -376,7 +376,7 @@ var prodiaFailedResponseHandler = (0, import_provider_utils.createJsonErrorRespo
 });
 
 // src/version.ts
-var VERSION = true ? "1.0.7" : "0.0.0-test";
+var VERSION = true ? "1.0.9" : "0.0.0-test";
 
 // src/prodia-provider.ts
 var defaultBaseURL = "https://inference.prodia.com/v2";

package/dist/index.mjs

@@ -362,7 +362,7 @@ var prodiaFailedResponseHandler = createJsonErrorResponseHandler({
 });
 
 // src/version.ts
-var VERSION = true ? "1.0.7" : "0.0.0-test";
+var VERSION = true ? "1.0.9" : "0.0.0-test";
 
 // src/prodia-provider.ts
 var defaultBaseURL = "https://inference.prodia.com/v2";

package/docs/65-prodia.mdx

@@ -0,0 +1,197 @@
+---
+title: Prodia
+description: Learn how to use Prodia models with the AI SDK.
+---
+
+# Prodia Provider
+
+[Prodia](https://prodia.com/) is a fast inference platform for generative AI, offering high-speed image generation with FLUX and Stable Diffusion models.
+
+## Setup
+
+The Prodia provider is available via the `@ai-sdk/prodia` module. You can install it with
+
+<Tabs items={['pnpm', 'npm', 'yarn', 'bun']}>
+  <Tab>
+    <Snippet text="pnpm add @ai-sdk/prodia" dark />
+  </Tab>
+  <Tab>
+    <Snippet text="npm install @ai-sdk/prodia" dark />
+  </Tab>
+  <Tab>
+    <Snippet text="yarn add @ai-sdk/prodia" dark />
+  </Tab>
+
+  <Tab>
+    <Snippet text="bun add @ai-sdk/prodia" dark />
+  </Tab>
+</Tabs>
+
+## Provider Instance
+
+You can import the default provider instance `prodia` from `@ai-sdk/prodia`:
+
+```ts
+import { prodia } from '@ai-sdk/prodia';
+```
+
+If you need a customized setup, you can import `createProdia` and create a provider instance with your settings:
+
+```ts
+import { createProdia } from '@ai-sdk/prodia';
+
+const prodia = createProdia({
+  apiKey: 'your-api-key', // optional, defaults to PRODIA_TOKEN environment variable
+  baseURL: 'custom-url', // optional
+  headers: {
+    /* custom headers */
+  }, // optional
+});
+```
+
+You can use the following optional settings to customize the Prodia provider instance:
+
+- **baseURL** _string_
+
+  Use a different URL prefix for API calls.
+  The default prefix is `https://inference.prodia.com/v2`.
+
+- **apiKey** _string_
+
+  API key that is being sent using the `Authorization` header as a Bearer token.
+  It defaults to the `PRODIA_TOKEN` environment variable.
+
+- **headers** _Record&lt;string,string&gt;_
+
+  Custom headers to include in the requests.
+
+- **fetch** _(input: RequestInfo, init?: RequestInit) => Promise&lt;Response&gt;_
+
+  Custom [fetch](https://developer.mozilla.org/en-US/docs/Web/API/fetch) implementation.
+  You can use it as a middleware to intercept requests,
+  or to provide a custom fetch implementation for e.g. testing.
+
+## Image Models
+
+You can create Prodia image models using the `.image()` factory method.
+For more on image generation with the AI SDK see [generateImage()](/docs/reference/ai-sdk-core/generate-image).
+
+### Basic Usage
+
+```ts
+import { writeFileSync } from 'node:fs';
+import { prodia } from '@ai-sdk/prodia';
+import { generateImage } from 'ai';
+
+const { image } = await generateImage({
+  model: prodia.image('inference.flux-fast.schnell.txt2img.v2'),
+  prompt: 'A cat wearing an intricate robe',
+});
+
+const filename = `image-${Date.now()}.png`;
+writeFileSync(filename, image.uint8Array);
+console.log(`Image saved to ${filename}`);
+```
+
+### Model Capabilities
+
+Prodia offers fast inference for various image generation models. Here are the supported model types:
+
+| Model                                    | Description                                          |
+| ---------------------------------------- | ---------------------------------------------------- |
+| `inference.flux-fast.schnell.txt2img.v2` | Fast FLUX Schnell model for text-to-image generation |
+| `inference.flux.schnell.txt2img.v2`      | FLUX Schnell model for text-to-image generation      |
+
+<Note>
+  Prodia supports additional model IDs. Check the [Prodia
+  documentation](https://docs.prodia.com/) for the full list of available
+  models.
+</Note>
+
+### Image Size
+
+You can specify the image size using the `size` parameter in `WIDTHxHEIGHT` format:
+
+```ts
+import { prodia } from '@ai-sdk/prodia';
+import { generateImage } from 'ai';
+
+const { image } = await generateImage({
+  model: prodia.image('inference.flux-fast.schnell.txt2img.v2'),
+  prompt: 'A serene mountain landscape at sunset',
+  size: '1024x768',
+});
+```
+
+### Provider Options
+
+Prodia image models support additional options through the `providerOptions.prodia` object:
+
+```ts
+import { prodia, type ProdiaImageProviderOptions } from '@ai-sdk/prodia';
+import { generateImage } from 'ai';
+
+const { image } = await generateImage({
+  model: prodia.image('inference.flux-fast.schnell.txt2img.v2'),
+  prompt: 'A cat wearing an intricate robe',
+  providerOptions: {
+    prodia: {
+      width: 1024,
+      height: 768,
+      steps: 4,
+      stylePreset: 'cinematic',
+    } satisfies ProdiaImageProviderOptions,
+  },
+});
+```
+
+The following provider options are supported:
+
+- **width** _number_ - Output width in pixels (256–1920). When set, this overrides any width derived from `size`.
+- **height** _number_ - Output height in pixels (256–1920). When set, this overrides any height derived from `size`.
+- **steps** _number_ - Number of computational iterations (1–4). More steps typically produce higher quality results.
+- **stylePreset** _string_ - Apply a visual theme to the output image. Supported presets: `3d-model`, `analog-film`, `anime`, `cinematic`, `comic-book`, `digital-art`, `enhance`, `fantasy-art`, `isometric`, `line-art`, `low-poly`, `neon-punk`, `origami`, `photographic`, `pixel-art`, `texture`, `craft-clay`.
+- **loras** _string[]_ - Augment the output with up to 3 LoRA models.
+- **progressive** _boolean_ - When using JPEG output, return a progressive JPEG.
+
+### Seed
+
+You can use the `seed` parameter to get reproducible results:
+
+```ts
+import { prodia } from '@ai-sdk/prodia';
+import { generateImage } from 'ai';
+
+const { image } = await generateImage({
+  model: prodia.image('inference.flux-fast.schnell.txt2img.v2'),
+  prompt: 'A serene mountain landscape at sunset',
+  seed: 12345,
+});
+```
+
+### Provider Metadata
+
+The `generateImage` response includes provider-specific metadata in `providerMetadata.prodia.images[]`. Each image object may contain the following properties:
+
+- **jobId** _string_ - The unique identifier for the generation job.
+- **seed** _number_ - The seed used for generation. Useful for reproducing results.
+- **elapsed** _number_ - Generation time in seconds.
+- **iterationsPerSecond** _number_ - Processing speed metric.
+- **createdAt** _string_ - Timestamp when the job was created.
+- **updatedAt** _string_ - Timestamp when the job was last updated.
+
+```ts
+import { prodia } from '@ai-sdk/prodia';
+import { generateImage } from 'ai';
+
+const { image, providerMetadata } = await generateImage({
+  model: prodia.image('inference.flux-fast.schnell.txt2img.v2'),
+  prompt: 'A serene mountain landscape at sunset',
+});
+
+// Access provider metadata
+const metadata = providerMetadata?.prodia?.images?.[0];
+console.log('Job ID:', metadata?.jobId);
+console.log('Seed:', metadata?.seed);
+console.log('Elapsed:', metadata?.elapsed);
+```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/prodia",
-  "version": "1.0.7",
+  "version": "1.0.9",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",
@@ -8,6 +8,7 @@
   "types": "./dist/index.d.ts",
   "files": [
     "dist/**/*",
+    "docs/**/*",
     "src",
     "!src/**/*.test.ts",
     "!src/**/*.test-d.ts",
@@ -15,6 +16,9 @@
     "!src/**/__fixtures__",
     "CHANGELOG.md"
   ],
+  "directories": {
+    "doc": "./docs"
+  },
   "exports": {
     "./package.json": "./package.json",
     ".": {
@@ -25,7 +29,7 @@
   },
   "dependencies": {
     "@ai-sdk/provider": "3.0.5",
-    "@ai-sdk/provider-utils": "4.0.9"
+    "@ai-sdk/provider-utils": "4.0.10"
   },
   "devDependencies": {
     "@types/node": "20.17.24",
@@ -58,7 +62,7 @@
   "scripts": {
     "build": "pnpm clean && tsup --tsconfig tsconfig.build.json",
     "build:watch": "pnpm clean && tsup --watch",
-    "clean": "del-cli dist *.tsbuildinfo",
+    "clean": "del-cli dist docs *.tsbuildinfo",
     "lint": "eslint \"./**/*.ts*\"",
     "type-check": "tsc --build",
     "prettier-check": "prettier --check \"./**/*.ts*\"",