lucataco/clip-interrogator ❓🖼️ → 📝

▶️ 123.1K runs 📅 Jul 2023 ⚙️ Cog 0.8.5 🔗 GitHub 📄 Paper ⚖️ License
image-to-prompt image-to-text

About

CLIP Interrogator (for faster inference)

Example Output

Output

painting of a turtle swimming in the ocean with a blue sky in the background, illustrative art, turtle, michael angelo inspired, world-bearing turtle, highly detailed illustration.”, 4k artwork, realistic illustration, highly detailed digital painting, vibrant digital painting, [ 4 k digital art, 4k art, hypperrealistic illustration, high detail illustration, vibrant realistic

Performance Metrics

0.90s Prediction Time
0.86s Total Time
All Input Parameters 
{
  "mode": "fast",
  "image": "https://replicate.delivery/pbxt/JVpnDt9nXuAnqBaXFPH8JbLrkU7JxQIoAGrHFwRWnFYqI7Ad/replicate-prediction-lyehbrdbrdztdi7ggx63lmhkgm.png",
  "clip_model_name": "ViT-bigG-14/laion2b_s39b_b160k"
}
Input Parameters
mode Default: best
Prompt mode (best takes 10-20 seconds, fast takes 1-2 seconds).
image (required) Type: string
Input image
clip_model_name Default: ViT-L-14/openai
Choose ViT-L for Stable Diffusion 1, ViT-H for Stable Diffusion 2, or ViT-bigG for Stable Diffusion XL.
Output Schema

Output

Type: string

Example Execution Logs 
0%|          | 0/55 [00:00<?, ?it/s]
 49%|████▉     | 27/55 [00:00<00:00, 265.22it/s]
 98%|█████████▊| 54/55 [00:00<00:00, 266.00it/s]
100%|██████████| 55/55 [00:00<00:00, 267.08it/s]
Version Details
Version ID
14d81f8a13e8ef87cc9b5eb7d03f5940fc7010e7226e93af612c5f0f4df1a35f
Version Created
September 12, 2023
Run on Replicate →