Flux 1 Srpo
Playground
Try it on WavespeedAI!FLUX.1 SRPO [dev] is a cutting-edge, 12-billion-parameter flow transformer designed to generate stunning, high-quality images from text with exceptional aesthetics. Perfect for both personal and commercial use.
Features
flux-1-srpo/text-to-image
FLUX.1 SRPO [dev] is a 12-billion-parameter rectified flow transformer built for text-to-image generation with breathtaking quality and artistic coherence. It transforms descriptive prompts into visually striking compositions that balance realism, imagination, and aesthetic precision — ideal for both personal and commercial creative work.
🌟 Key Features
-
High-Fidelity Generation Produces detailed, compositionally rich images from even abstract or poetic prompts.
-
Artistic Interpretation Captures lighting, texture, and emotion in a way that feels painterly yet realistic.
-
Configurable Creativity Adjust parameters like guidance scale, inference steps, and strength to control realism, style, and variation.
-
Resolution Control Flexible output sizes — up to 1024×1024 pixels — perfect for design, print, or digital use.
-
Multi-Format Output Export in JPEG or PNG to fit any creative pipeline.
-
Developer-Friendly [dev] Build Optimized for experimentation and fast inference; ideal for both research and production.
⚙️ Capabilities
-
Input: Text prompt
-
Output: High-resolution image (JPEG / PNG)
-
Adjustable Parameters:
- width / height
- strength
- num_inference_steps
- guidance_scale
- seed
🧩 Quick Start
-
Write your prompt — describe the scene or concept in detail.
-
Set image size — e.g., 1024×1024 for square artworks.
-
Adjust strength & guidance — balance realism and creativity.
-
Run generation — preview the image; tweak parameters if needed.
-
Download output — available in JPEG or PNG formats.
💰 Pricing
Each generation costs only $0.025 per image.
💡 Best Use Cases
- Concept Art & Illustration — Generate imaginative visuals from narrative prompts.
- Photography & Fashion Design — Create surreal or editorial-style compositions.
- Advertising & Branding — Craft eye-catching visuals for campaigns or moodboards.
- Fine Art Creation — Experiment with visual metaphors and artistic reinterpretation.
📝 Notes
- Prompts with rich visual details yield the most coherent and expressive results.
- Adjust guidance scale for balance between creativity and accuracy.
- Available output formats: JPEG and PNG.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-1-srpo" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"size": "1024*1024",
"strength": 0.8,
"num_inference_steps": 28,
"seed": -1,
"guidance_scale": 3.5,
"output_format": "jpeg",
"enable_base64_output": false,
"enable_sync_mode": false
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| size | string | No | 1024*1024 | 256 ~ 1536 per dimension | The size of the generated media in pixels (width*height). |
| strength | number | No | 0.8 | 0.00 ~ 1.00 | Strength indicates extent to transform the reference image. |
| num_inference_steps | integer | No | 28 | 1 ~ 50 | The number of inference steps to perform. |
| seed | integer | No | -1 | -1 ~ 2147483647 | The random seed to use for the generation. -1 means a random seed will be used. |
| guidance_scale | number | No | 3.5 | 1.0 ~ 20.0 | The guidance scale to use for the generation. |
| output_format | string | No | jpeg | jpeg, png | The format of the output image. |
| enable_base64_output | boolean | No | false | - | If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API. |
| enable_sync_mode | boolean | No | false | - | If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |