Pruna AI
P-Image
Generate one raster image from text at a chosen aspect ratio or custom size. Bring your own compatible LoRA and adjust its strength across a series.
pruna/p-imageBest for
- Try different compositions for a campaign concept
- Generate a character or visual style from a trained LoRA
Technical details
Read the model documentation- API model ID
pruna/p-image- Provider
- Pruna AI
- Modality
- Image
- Input
- Text prompt
- Output
- Image
- Endpoint
POST /v2/jobs- Workflow
- Text to image
Request parameters
promptstring · RequiredWhat to draw.
heightintegerHeight in pixels, 256 to 1440 and a multiple of 16. Only with aspect_ratio custom.
widthintegerWidth in pixels, 256 to 1440 and a multiple of 16. Only with aspect_ratio custom.
aspect_ratiostringShape of the picture: 1:1, 16:9 (default), 9:16, 4:3, 3:4, 3:2, 2:3, or custom, which takes width and height instead.
disable_safety_checkerbooleanFixed for this model; leave it out
- false
Additional parameters
enable_copyright_filterbooleanTurns on a check of the prompt: a prompt that asks for a copyrighted character, a trademark or logo, or a real person's likeness is refused.
- The input images are not checked.
- Default false;
- no price change.
hf_api_tokenstringHugging Face token for a private LoRA. It travels to the generator with the request, so use a read-only one.
lora_scalenumberHow strongly the LoRA applies, from -1 to 3. Default 0.5.
lora_weightsstringYour own LoRA, in the form the generator's documentation gives.
prompt_upsamplingbooleanLets the generator expand a short prompt before drawing. Default false.
seedintegerFixes the random draw: the same inputs and seed give the same result.
Pricing
| Billable unit and options | Rate (USD) |
|---|---|
| Per image | $0.005 |
Catalogue rates on 21 Nov 2026. Prices exclude VAT.
View in pricing catalogue