prunaai/p-image 🔢📝❓✓ → 🖼️

⭐ Official ▶️ 14.0M runs 📅 Oct 2025 ⚙️ Cog 0.16.12 🔗 GitHub ⚖️ License
text-rendering text-to-image

Performance

0.7sTypical run time
14.0MTotal runs

About

A sub 1 second text-to-image model built for production use cases.

Example Output

Prompt:

"A schoolgirl with long dark hair, light jacket, and skirt, standing on a balcony beside a black cat and looking over the city, cinematic anime background art with soft atmospheric perspective, cool blue monochrome lighting, gentle wind, and melancholic slice-of-life mood, above blurred rooftops, distant mountains, evening haze, and tiny warm city lights at dusk."

Output

Example output

Performance Metrics

0.66s Prediction Time
0.67s Total Time
All Input Parameters 
{
  "prompt": "A schoolgirl with long dark hair, light jacket, and skirt, standing on a balcony beside a black cat and looking over the city, cinematic anime background art with soft atmospheric perspective, cool blue monochrome lighting, gentle wind, and melancholic slice-of-life mood, above blurred rooftops, distant mountains, evening haze, and tiny warm city lights at dusk.",
  "lora_scale": 0.5,
  "aspect_ratio": "2:3",
  "prompt_upsampling": false
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation.
width Type: integerRange: 256 - 1440
Width of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16.
height Type: integerRange: 256 - 1440
Height of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16.
prompt (required) Type: string
Text prompt for image generation.
lora_scale Type: numberDefault: 0.5Range: -1 - 3
Determines how strongly the main LoRA should be applied. 0.5 usually works well for most LoRAs.
aspect_ratio Default: 16:9
Aspect ratio for the generated image.
hf_api_token Type: string
HuggingFace API token. If you're using a HuggingFace LoRAs that needs authentication, you'll need to provide an API token.
lora_weights Type: string
Load LoRA weights. Supports HuggingFace URLs in the format huggingface.co/<owner>/<model-name>[/<lora-weights-file.safetensors>]. HuggingFace LoRAs may require an API token to access, which you can provide in the `hf_api_token` input.
prompt_upsampling Type: booleanDefault: false
Upsample the prompt with an LLM.
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images.
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Using seed: 50575
  0%|          | 0/8 [00:00<?, ?it/s]
 38%|███▊      | 3/8 [00:00<00:00, 20.66it/s]
 75%|███████▌  | 6/8 [00:00<00:00, 17.51it/s]
100%|██████████| 8/8 [00:00<00:00, 16.90it/s]
100%|██████████| 8/8 [00:00<00:00, 17.37it/s]
Generation took 0.63 seconds
Version Details
Version ID
79bbabc34e1dc2c55b09a5a8a220d7792f77234c5aded9b074bdf6bf783a2f65
Version Created
June 19, 2026
Run on Replicate →