tencentarc/photomaker 🔢📝❓🖼️✓ → 🖼️

▶️ 8.3M runs 📅 Jan 2024 ⚙️ Cog 0.9.0-beta12 🔗 GitHub 📄 Paper ⚖️ License
image-consistent-character-generation image-to-image

About

Create photos, paintings and avatars for anyone in any style within seconds.

Example Output

Prompt:

"A photo of a scientist img receiving the Nobel Prize"

Output

Example output

Performance Metrics

11.85s Prediction Time
11.86s Total Time
All Input Parameters 
{
  "prompt": "A photo of a scientist img receiving the Nobel Prize",
  "num_steps": 50,
  "style_name": "Photographic (Default)",
  "input_image": "https://replicate.delivery/pbxt/KFkSv1oX0v3e7GnOrmzULGqCA8222pC6FI2EKcfuCZWxvHN3/newton_0.jpg",
  "num_outputs": 1,
  "guidance_scale": 5,
  "negative_prompt": "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
  "style_strength_ratio": 20
}
Input Parameters
seed Type: integerRange: 0 - 2147483647
Seed. Leave blank to use a random number
prompt Type: stringDefault: A photo of a person img
Prompt. Example: 'a photo of a man/woman img'. The phrase 'img' is the trigger word.
num_steps Type: integerDefault: 20Range: 1 - 100
Number of sample steps
style_name Default: Photographic (Default)
Style template. The style template will add a style-specific prompt and negative prompt to the user's prompt.
input_image (required) Type: string
The input image, for example a photo of your face.
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of output images
input_image2 Type: string
Additional input image (optional)
input_image3 Type: string
Additional input image (optional)
input_image4 Type: string
Additional input image (optional)
guidance_scale Type: numberDefault: 5Range: 1 - 10
Guidance scale. A guidance scale of 1 corresponds to doing no classifier free guidance.
negative_prompt Type: stringDefault: nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
Negative Prompt. The negative prompt should NOT contain the trigger word.
style_strength_ratio Type: numberDefault: 20Range: 15 - 50
Style strength (%)
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images.
Output Schema

Output

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

Example Execution Logs 
Using seed 932038239...
Loading image /tmp/tmp3rl4689rnewton_0.jpg...
Setting seed...
Start inference...
[Debug] Prompt: cinematic photo A photo of a scientist img receiving the Nobel Prize . 35mm photograph, film, bokeh, professional, 4k, highly detailed
[Debug] Neg Prompt: drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
Start merge step: 10
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:09,  4.95it/s]
  4%|▍         | 2/50 [00:00<00:09,  4.96it/s]
  6%|▌         | 3/50 [00:00<00:09,  4.98it/s]
  8%|▊         | 4/50 [00:00<00:09,  4.99it/s]
 10%|█         | 5/50 [00:01<00:09,  5.00it/s]
 12%|█▏        | 6/50 [00:01<00:08,  5.00it/s]
 14%|█▍        | 7/50 [00:01<00:08,  5.01it/s]
 16%|█▌        | 8/50 [00:01<00:08,  5.01it/s]
 18%|█▊        | 9/50 [00:01<00:08,  5.01it/s]
 20%|██        | 10/50 [00:02<00:07,  5.01it/s]
 22%|██▏       | 11/50 [00:02<00:07,  5.01it/s]
 24%|██▍       | 12/50 [00:02<00:07,  5.00it/s]
 26%|██▌       | 13/50 [00:02<00:07,  5.00it/s]
 28%|██▊       | 14/50 [00:02<00:07,  5.00it/s]
 30%|███       | 15/50 [00:03<00:06,  5.00it/s]
 32%|███▏      | 16/50 [00:03<00:06,  5.00it/s]
 34%|███▍      | 17/50 [00:03<00:06,  5.00it/s]
 36%|███▌      | 18/50 [00:03<00:06,  5.00it/s]
 38%|███▊      | 19/50 [00:03<00:06,  4.98it/s]
 40%|████      | 20/50 [00:04<00:06,  4.98it/s]
 42%|████▏     | 21/50 [00:04<00:05,  4.98it/s]
 44%|████▍     | 22/50 [00:04<00:05,  4.98it/s]
 46%|████▌     | 23/50 [00:04<00:05,  4.97it/s]
 48%|████▊     | 24/50 [00:04<00:05,  4.97it/s]
 50%|█████     | 25/50 [00:05<00:05,  4.98it/s]
 52%|█████▏    | 26/50 [00:05<00:04,  4.98it/s]
 54%|█████▍    | 27/50 [00:05<00:04,  4.97it/s]
 56%|█████▌    | 28/50 [00:05<00:04,  4.96it/s]
 58%|█████▊    | 29/50 [00:05<00:04,  4.96it/s]
 60%|██████    | 30/50 [00:06<00:04,  4.96it/s]
 62%|██████▏   | 31/50 [00:06<00:03,  4.96it/s]
 64%|██████▍   | 32/50 [00:06<00:03,  4.95it/s]
 66%|██████▌   | 33/50 [00:06<00:03,  4.95it/s]
 68%|██████▊   | 34/50 [00:06<00:03,  4.95it/s]
 70%|███████   | 35/50 [00:07<00:03,  4.95it/s]
 72%|███████▏  | 36/50 [00:07<00:02,  4.95it/s]
 74%|███████▍  | 37/50 [00:07<00:02,  4.95it/s]
 76%|███████▌  | 38/50 [00:07<00:02,  4.95it/s]
 78%|███████▊  | 39/50 [00:07<00:02,  4.94it/s]
 80%|████████  | 40/50 [00:08<00:02,  4.93it/s]
 82%|████████▏ | 41/50 [00:08<00:01,  4.93it/s]
 84%|████████▍ | 42/50 [00:08<00:01,  4.93it/s]
 86%|████████▌ | 43/50 [00:08<00:01,  4.93it/s]
 88%|████████▊ | 44/50 [00:08<00:01,  4.93it/s]
 90%|█████████ | 45/50 [00:09<00:01,  4.93it/s]
 92%|█████████▏| 46/50 [00:09<00:00,  4.93it/s]
 94%|█████████▍| 47/50 [00:09<00:00,  4.93it/s]
 96%|█████████▌| 48/50 [00:09<00:00,  4.92it/s]
 98%|█████████▊| 49/50 [00:09<00:00,  4.92it/s]
100%|██████████| 50/50 [00:10<00:00,  4.92it/s]
100%|██████████| 50/50 [00:10<00:00,  4.96it/s]
Running safety checker...
Saving images to file...
Version Details
Version ID
ddfc2b08d209f9fa8c1eca692712918bd449f695dabb4a958da31802a9570fe4
Version Created
January 19, 2024
Run on Replicate →