lucataco/ip_adapter-sdxl-face 🔢🖼️📝 → 🖼️

▶️ 34.2K runs 📅 Nov 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License
image-consistent-character-generation image-to-image

About

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate SDXL images with an image prompt

Example Output

Prompt:

"photo of a beautiful girl wearing casual shirt in a garden"

Output

Example output

Performance Metrics

16.23s Prediction Time
16.18s Total Time
All Input Parameters 
{
  "seed": 42,
  "image": "https://replicate.delivery/pbxt/JqifieOm5VA07pzpBWY4BNr2cf9YpQRjbGT3wBYFx9ANENSf/ai_face2.png",
  "scale": 0.6,
  "prompt": "photo of a beautiful girl wearing casual shirt in a garden",
  "num_outputs": 1,
  "negative_prompt": "",
  "num_inference_steps": 30
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
image (required) Type: string
Input face image
scale Type: numberDefault: 0.6Range: 0 - 1
Scale (influence of input image on generation)
prompt Type: stringDefault:
Prompt (leave blank for image variations)
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to output.
negative_prompt Type: stringDefault:
Negative Prompt
num_inference_steps Type: integerDefault: 30Range: 1 - 500
Number of denoising steps
Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs 
Using seed: 42
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:04,  6.18it/s]
  7%|▋         | 2/30 [00:00<00:04,  6.22it/s]
 10%|█         | 3/30 [00:00<00:04,  5.97it/s]
 13%|█▎        | 4/30 [00:00<00:04,  6.07it/s]
 17%|█▋        | 5/30 [00:00<00:04,  6.13it/s]
 20%|██        | 6/30 [00:00<00:03,  6.16it/s]
 23%|██▎       | 7/30 [00:01<00:03,  6.21it/s]
 27%|██▋       | 8/30 [00:01<00:03,  6.21it/s]
 30%|███       | 9/30 [00:01<00:03,  6.07it/s]
 33%|███▎      | 10/30 [00:01<00:03,  6.13it/s]
 37%|███▋      | 11/30 [00:01<00:03,  6.18it/s]
 40%|████      | 12/30 [00:01<00:02,  6.20it/s]
 43%|████▎     | 13/30 [00:02<00:02,  6.23it/s]
 47%|████▋     | 14/30 [00:02<00:02,  6.23it/s]
 50%|█████     | 15/30 [00:02<00:02,  6.18it/s]
 53%|█████▎    | 16/30 [00:02<00:02,  6.20it/s]
 57%|█████▋    | 17/30 [00:02<00:02,  6.19it/s]
 60%|██████    | 18/30 [00:02<00:01,  6.18it/s]
 63%|██████▎   | 19/30 [00:03<00:01,  6.15it/s]
 67%|██████▋   | 20/30 [00:03<00:01,  6.14it/s]
 70%|███████   | 21/30 [00:03<00:01,  6.13it/s]
 73%|███████▎  | 22/30 [00:03<00:01,  6.11it/s]
 77%|███████▋  | 23/30 [00:03<00:01,  6.15it/s]
 80%|████████  | 24/30 [00:03<00:00,  6.14it/s]
 83%|████████▎ | 25/30 [00:04<00:00,  6.16it/s]
 87%|████████▋ | 26/30 [00:04<00:00,  6.20it/s]
 90%|█████████ | 27/30 [00:04<00:00,  6.23it/s]
 93%|█████████▎| 28/30 [00:04<00:00,  6.10it/s]
 97%|█████████▋| 29/30 [00:04<00:00,  6.14it/s]
100%|██████████| 30/30 [00:04<00:00,  6.16it/s]
100%|██████████| 30/30 [00:04<00:00,  6.16it/s]
Version Details
Version ID
226c6bf67a75a129b0f978e518fed33e1fb13956e15761c1ac53c9d2f898c9af
Version Created
November 11, 2023
Run on Replicate →