prunaai/p-image 🔢📝❓✓ → 🖼️

⭐ Official ▶️ 18.1M runs 📅 Oct 2025 ⚙️ Cog 0.18.0 🔗 GitHub ⚖️ License
text-rendering text-to-image

Performance

1.2sTypical run time
18.1MTotal runs

About

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

Example Output

Prompt:

"Two women in flowing pastel lavender and pale blue dresses, holding hands while walking on a beach at sunset, romantic impressionist oil painting with thick palette-knife impasto, soft pastel colors, gold leaf accents, and dreamy texture, beside gentle waves reflecting a peach sun, distant cliffs, blush-pink clouds, cream sky strokes, and a peaceful nostalgic coastal atmosphere. In the very center, beautifully and largely written: "P-Image". The letters are painted in metallic gold paint, with visible brush strokes, uneven hand-painted edges, thick impasto texture, palette-knife ridges, small bristle marks, and subtle gold-leaf shine. The text should look like it was physically painted onto the canvas, not like a digital font."

Output

Example output

Performance Metrics

1.24s Prediction Time
1.26s Total Time
All Input Parameters 
{
  "seed": 0,
  "prompt": "Two women in flowing pastel lavender and pale blue dresses, holding hands while walking on a beach at sunset, romantic impressionist oil painting with thick palette-knife impasto, soft pastel colors, gold leaf accents, and dreamy texture, beside gentle waves reflecting a peach sun, distant cliffs, blush-pink clouds, cream sky strokes, and a peaceful nostalgic coastal atmosphere. In the very center, beautifully and largely written: \"P-Image\". The letters are painted in metallic gold paint, with visible brush strokes, uneven hand-painted edges, thick impasto texture, palette-knife ridges, small bristle marks, and subtle gold-leaf shine. The text should look like it was physically painted onto the canvas, not like a digital font.",
  "lora_scale": 0.5,
  "aspect_ratio": "2:3",
  "prompt_upsampling": true
}
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: 0
  0%|          | 0/8 [00:00<?, ?it/s]
 38%|███▊      | 3/8 [00:00<00:00, 20.19it/s]
 75%|███████▌  | 6/8 [00:00<00:00, 17.09it/s]
100%|██████████| 8/8 [00:00<00:00, 16.45it/s]
100%|██████████| 8/8 [00:00<00:00, 16.92it/s]
Generation took 0.65 seconds
Version Details
Version ID
10b739c5e107d9684e9e7eca6f443ab0861bd526af50a03cf42d6210b36684b7
Version Created
August 20, 2026
Run on Replicate →