Pruna Ai P Image Text To Image
Playground
Try it on WavespeedAI!Pruna AI P-Image Text to Image is a fast AI image generation model that creates high-quality images from text prompts. Ready-to-use REST inference API for creative design, marketing visuals, concept art, social media content, product mockups, and image generation workflows with simple integration, no coldstarts, and affordable pricing.
Features
Pruna AI P-Image Text-to-Image
Pruna AI P-Image Text-to-Image generates images from natural-language prompts with flexible size controls, custom aspect ratios, and reproducible outputs through seed support. It is suitable for portraits, product visuals, concept art, marketing creatives, and other prompt-driven image generation workflows.
Why Choose This?
-
Prompt-based image generation Turn natural-language descriptions into polished images for creative and commercial use.
-
Flexible aspect ratio control Use preset aspect ratios or switch to
customfor direct width and height control. -
Custom image dimensions Set
widthandheightto better match delivery requirements for web, social, ads, and design workflows. -
Multiple output formats Export generated images as
pngor other supported formats depending on your workflow. -
Seed support for reproducibility Use
seedto reproduce results more consistently across generations. -
Affordable fixed pricing Generate images at a simple flat cost per run.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired image. |
| aspect_ratio | No | Output aspect ratio. Can use a preset ratio or custom. |
| width | No | Output image width. Only takes effect when aspect_ratio is set to custom. |
| height | No | Output image height. Only takes effect when aspect_ratio is set to custom. |
| output_format | No | Output image format, such as png. |
| seed | No | Random seed for reproducibility. Use the same seed to get more consistent results. |
How to Use
- Write your prompt — describe the subject, style, lighting, composition, and mood you want.
- Choose aspect ratio — use a preset ratio or select
customif you want direct control over width and height. - Set width and height (optional) — these only take effect when
aspect_ratiois set tocustom. - Choose output format — select the format that best fits your workflow.
- Set a seed (optional) — use a fixed seed for more reproducible generations.
- Submit — run the model and download the generated image.
Example Prompt
A clean studio portrait of an adult US female model against a soft beige background, natural makeup, elegant neutral outfit, calm confident expression, soft diffused studio lighting, premium commercial photography, photorealistic, ultra-detailed, refined composition
Pricing
Just $0.005 per image.
Best Use Cases
- Portrait generation — Create polished studio-style or lifestyle portraits from prompts.
- Marketing creatives — Generate ad visuals, banners, and campaign assets quickly.
- Product concept imagery — Produce mockups and clean commercial scenes from text instructions.
- Social media content — Create prompt-driven visuals sized for posts, stories, and promotional content.
- Concept art and ideation — Explore visual directions rapidly with prompt and seed control.
- Custom-size image generation — Match output dimensions to specific design or publishing requirements.
Pro Tips
- Be specific in your prompt about subject, style, lighting, background, and mood.
- Use
customaspect ratio when you need exact width and height for a delivery format. - Keep the same
seedwhen you want to iterate on a concept with more consistent outputs. - Use
pngwhen image quality matters more than file size. - Start with smaller dimensions for rapid testing, then refine once the prompt direction is working.
- Short, focused prompts often give more controllable results than overly long descriptions.
Notes
promptis the only required field.widthandheightonly take effect whenaspect_ratiois set tocustom.seedhelps with reproducibility but may not guarantee identical results in every case.- Pricing is fixed at $0.005 per image.
Related Models
- Other Pruna AI image generation and image editing models may be useful when you need different quality, speed, or workflow trade-offs.
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/pruna-ai/p-image/text-to-image" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"aspect_ratio": "custom",
"width": 512,
"height": 512,
"output_format": "png",
"seed": -1,
"enable_sync_mode": false,
"enable_base64_output": false
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${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 generation. | |
| aspect_ratio | string | No | custom | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, custom | Aspect ratio of the generated image. |
| width | integer | No | 512 | 256 ~ 1440 | Custom width in pixels. Only used when aspect_ratio is custom. Must be a multiple of 16. |
| height | integer | No | 512 | 256 ~ 1440 | Custom height in pixels. Only used when aspect_ratio is custom. Must be a multiple of 16. |
| output_format | string | No | png | png, jpeg, webp | Output image format. |
| seed | integer | No | -1 | -1 ~ 2147483647 | Random seed. -1 means random. |
| 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. |
| 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. |
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.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 |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
| data.model | string | Model ID used for the prediction |
| data.outputs | string | Array of URLs to the generated content. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| 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 |