deepai.org APIdeepai.org ↗
Generate AI images from text prompts using 123+ art styles via the DeepAI API. Returns base64-encoded images with metadata including dimensions and job ID.
curl -X POST 'https://api.parse.bot/scraper/7ed530f5-9d88-47ce-93e2-9c2e596b7f77/generate_image' \
-H 'X-API-Key: $PARSE_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"text": "a mountain landscape"
}'Generate an AI image from a text prompt. Submits the prompt to DeepAI's text-to-image API and returns the generated image as a base64-encoded string along with metadata. Generation typically takes 5-15 seconds.
| Param | Type | Description |
|---|---|---|
| textrequired | string | The text prompt describing the image to generate (e.g. 'a beautiful sunset over the ocean') |
| style | string | Art style/model to use. Accepted values include: text2img, cyberpunk-generator, anime-portrait-generator, fantasy-world-generator, pixel-art-generator, watercolor-painting-generator, logo-generator, pop-art-generator, steampunk-generator, and 114 more. Use list_styles endpoint for the full list of 123 accepted slugs. |
| width | integer | Image width in pixels (128-1536) |
| height | integer | Image height in pixels (128-1536) |
| quality | string | Quality preference. Accepted values: 'true' for higher quality (slower), 'false' for faster generation. |
{
"type": "object",
"fields": {
"style": "string - The style/model used",
"width": "integer - Image width in pixels",
"height": "integer - Image height in pixels",
"job_id": "string - Unique job identifier",
"prompt": "string - The text prompt used",
"image_url": "string - Direct URL to the generated image",
"content_type": "string - MIME type of the image (e.g. image/jpeg)",
"image_base64": "string - Base64-encoded image data",
"image_size_bytes": "integer - Size of the image in bytes"
},
"sample": {
"data": {
"style": "text2img",
"width": 640,
"height": 640,
"job_id": "ace4fcf3-7b26-493d-a370-5107abe82a77",
"prompt": "a blue ocean wave",
"image_url": "https://api.deepai.org/job-view-file/ace4fcf3-7b26-493d-a370-5107abe82a77/outputs/output.jpg",
"content_type": "image/jpeg",
"image_base64": "/9j/4AAQSkZJRgABAQAAAQABAAD/...[base64 data]...",
"image_size_bytes": 60332
},
"status": "success"
}
}About the deepai.org API
This API gives you two endpoints — generate_image and list_styles — to create AI-generated images from text prompts across 123+ art styles and retrieve the full style catalog. Call generate_image with a text prompt and optional style slug, and the response includes a base64-encoded image, a direct image_url, pixel dimensions, MIME type, file size in bytes, and a job_id for tracking the generation.
Generating Images
The generate_image endpoint accepts a required text prompt and several optional parameters: style (the art style slug), width and height (each between 128 and 1536 pixels), and quality ('true' for higher fidelity at the cost of speed, 'false' for faster output). Generation typically completes in 5–15 seconds. The response carries both image_base64 (the full image data, ready to decode and save) and image_url (a direct link to the hosted file), along with content_type, image_size_bytes, and the echoed prompt and style values.
Browsing Available Styles
The list_styles endpoint takes no inputs and returns a flat array of all supported styles, each with a slug and a human-readable name. The slug value maps directly to the style parameter in generate_image. With 123+ styles currently available — including options like cyberpunk-generator, anime-portrait-generator, and watercolor — you can enumerate the catalog programmatically rather than maintaining a hardcoded list.
Response Shape and Dimensions
Every generate_image response includes width and height fields reflecting the actual output dimensions, which may be influenced by the chosen style's defaults if you omit those parameters. The job_id field provides a unique identifier per generation. There is no pagination on list_styles — all styles are returned in a single response with a total_styles count.
- Generating style-specific concept art by passing a scene description and a style slug from
list_styles - Building image variation tools that loop over multiple style slugs with the same prompt and compare outputs
- Automating social media asset creation by converting product copy into images using the
image_urlresponse field - Creating game asset prototypes by targeting styles like pixel art or fantasy and specifying exact
width/heightdimensions - Embedding on-demand image generation into content management systems using the
image_base64field for direct upload - Cataloging all available styles into a UI selector by consuming the
slugandnamefields fromlist_styles
| Tier | Price | Credits/month | Rate limit |
|---|---|---|---|
| Free | $0/mo | 100 | 5 req/min |
| Hobby | $30/mo | 1,000 | 20 req/min |
| Developer | $100/mo | 5,000 | 250 req/min |
One credit = one API call regardless of which marketplace API you call. Exceeding the rate limit returns a 429 response. Authenticate with the X-API-Key header.
Does DeepAI have an official developer API?+
What does the `generate_image` endpoint actually return beyond the image itself?+
image_base64 (the full encoded image data), image_url (a hosted direct link), content_type (MIME type such as image/jpeg), image_size_bytes, the actual output width and height in pixels, the job_id for this generation, and the prompt and style values that were used.Is there a way to retrieve a previously generated image by job_id?+
generate_image and style listing via list_styles, but does not expose an endpoint to look up past jobs by their job_id. You can fork this API on Parse and revise it to add a job-retrieval endpoint.Can I request an image at any resolution, including very large sizes?+
Does the API support negative prompts or other advanced generation controls?+
generate_image endpoint accepts text, style, width, height, and quality. Parameters like negative prompts, seed values, or guidance scale are not exposed. You can fork this API on Parse and revise it to add those controls if the underlying model supports them.