lucataco/ip_adapter-face 🔢🖼️📝 → 🖼️
About
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate SDv1.5 images with an image prompt
Example Output
Prompt:
"photo of a beautiful girl wearing casual shirt in a garden"
Output
Performance Metrics
7.79s
Prediction Time
7.77s
Total Time
All Input Parameters
{
"seed": 15251,
"image": "https://replicate.delivery/pbxt/Jqd79M3DQVfYYvYcZYURBMxc0kd3oeM9Z5jiYSUONnHEfhlW/ai_face2.png",
"prompt": "photo of a beautiful girl wearing casual shirt in a garden",
"num_outputs": 1,
"num_inference_steps": 50
}
Input Parameters
- seed
- Random seed. Leave blank to randomize the seed
- image
- Input face image
- prompt
- Prompt
- num_outputs
- Number of images to output.
- num_inference_steps
- Number of denoising steps
Output Schema
Output
Example Execution Logs
Using seed: 15251 0%| | 0/50 [00:00<?, ?it/s] 6%|▌ | 3/50 [00:00<00:01, 23.79it/s] 12%|█▏ | 6/50 [00:00<00:01, 23.63it/s] 18%|█▊ | 9/50 [00:00<00:01, 23.58it/s] 24%|██▍ | 12/50 [00:00<00:01, 23.56it/s] 30%|███ | 15/50 [00:00<00:01, 23.52it/s] 36%|███▌ | 18/50 [00:00<00:01, 23.49it/s] 42%|████▏ | 21/50 [00:00<00:01, 23.45it/s] 48%|████▊ | 24/50 [00:01<00:01, 23.44it/s] 54%|█████▍ | 27/50 [00:01<00:00, 23.41it/s] 60%|██████ | 30/50 [00:01<00:00, 23.39it/s] 66%|██████▌ | 33/50 [00:01<00:00, 23.39it/s] 72%|███████▏ | 36/50 [00:01<00:00, 23.38it/s] 78%|███████▊ | 39/50 [00:01<00:00, 23.40it/s] 84%|████████▍ | 42/50 [00:01<00:00, 23.38it/s] 90%|█████████ | 45/50 [00:01<00:00, 23.39it/s] 96%|█████████▌| 48/50 [00:02<00:00, 23.35it/s] 100%|██████████| 50/50 [00:02<00:00, 23.42it/s]
Version Details
- Version ID
b6618893d3d0ee4a9b3a1e990a00be6bd6c3b6fddef83e0b68efc525de54580c- Version Created
- November 9, 2023