tencentarc/photomaker-style 🔢📝❓🖼️✓ → 🖼️

▶️ 1.5M runs 📅 Jan 2024 ⚙️ Cog 0.9.2 🔗 GitHub 📄 Paper ⚖️ License
avatar-generation image-consistent-character-generation image-style-transfer image-to-image

About

Create photos, paintings and avatars for anyone in any style within seconds. (Stylization version)

Example Output

Prompt:

"A girl img riding dragon over a whimsical castle, 3d CGI, art by Pixar, half-body, screenshot from animation"

Output

Example outputExample output

Performance Metrics

22.72s Prediction Time
22.81s Total Time
All Input Parameters 
{
  "prompt": "A girl img riding dragon over a whimsical castle, 3d CGI, art by Pixar, half-body, screenshot from animation",
  "num_steps": 50,
  "style_name": "(No style)",
  "input_image": "https://replicate.delivery/pbxt/KFRveCbE71qFTQGSF509CXYC16qB1bcZmAWq8O172ael04Ga/lenna.jpg",
  "num_outputs": 2,
  "guidance_scale": 5,
  "negative_prompt": "realistic, photo-realistic, worst quality, greyscale, bad anatomy, bad hands, error, text",
  "style_strength_ratio": 35
}
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: (No style)
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 1456680131...
Loading image /tmp/tmpi4x8dydelenna.jpg...
Setting seed...
Start inference...
[Debug] Prompt: A girl img riding dragon over a whimsical castle, 3d CGI, art by Pixar, half-body, screenshot from animation
[Debug] Neg Prompt:  realistic, photo-realistic, worst quality, greyscale, bad anatomy, bad hands, error, text
Start merge step: 17
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:11,  4.33it/s]
  4%|▍         | 2/50 [00:00<00:15,  3.18it/s]
  6%|▌         | 3/50 [00:00<00:16,  2.92it/s]
  8%|▊         | 4/50 [00:01<00:16,  2.81it/s]
 10%|█         | 5/50 [00:01<00:16,  2.76it/s]
 12%|█▏        | 6/50 [00:02<00:16,  2.70it/s]
 14%|█▍        | 7/50 [00:02<00:16,  2.69it/s]
 16%|█▌        | 8/50 [00:02<00:15,  2.68it/s]
 18%|█▊        | 9/50 [00:03<00:15,  2.67it/s]
 20%|██        | 10/50 [00:03<00:14,  2.67it/s]
 22%|██▏       | 11/50 [00:03<00:14,  2.66it/s]
 24%|██▍       | 12/50 [00:04<00:14,  2.66it/s]
 26%|██▌       | 13/50 [00:04<00:13,  2.66it/s]
 28%|██▊       | 14/50 [00:05<00:13,  2.65it/s]
 30%|███       | 15/50 [00:05<00:13,  2.65it/s]
 32%|███▏      | 16/50 [00:05<00:12,  2.65it/s]
 34%|███▍      | 17/50 [00:06<00:12,  2.65it/s]
 36%|███▌      | 18/50 [00:06<00:12,  2.64it/s]
 38%|███▊      | 19/50 [00:07<00:11,  2.64it/s]
 40%|████      | 20/50 [00:07<00:11,  2.64it/s]
 42%|████▏     | 21/50 [00:07<00:10,  2.65it/s]
 44%|████▍     | 22/50 [00:08<00:10,  2.64it/s]
 46%|████▌     | 23/50 [00:08<00:10,  2.64it/s]
 48%|████▊     | 24/50 [00:08<00:09,  2.64it/s]
 50%|█████     | 25/50 [00:09<00:09,  2.64it/s]
 52%|█████▏    | 26/50 [00:09<00:09,  2.64it/s]
 54%|█████▍    | 27/50 [00:10<00:08,  2.64it/s]
 56%|█████▌    | 28/50 [00:10<00:08,  2.64it/s]
 58%|█████▊    | 29/50 [00:10<00:07,  2.64it/s]
 60%|██████    | 30/50 [00:11<00:07,  2.63it/s]
 62%|██████▏   | 31/50 [00:11<00:07,  2.63it/s]
 64%|██████▍   | 32/50 [00:11<00:06,  2.63it/s]
 66%|██████▌   | 33/50 [00:12<00:06,  2.63it/s]
 68%|██████▊   | 34/50 [00:12<00:06,  2.63it/s]
 70%|███████   | 35/50 [00:13<00:05,  2.63it/s]
 72%|███████▏  | 36/50 [00:13<00:05,  2.63it/s]
 74%|███████▍  | 37/50 [00:13<00:04,  2.63it/s]
 76%|███████▌  | 38/50 [00:14<00:04,  2.63it/s]
 78%|███████▊  | 39/50 [00:14<00:04,  2.63it/s]
 80%|████████  | 40/50 [00:14<00:03,  2.63it/s]
 82%|████████▏ | 41/50 [00:15<00:03,  2.63it/s]
 84%|████████▍ | 42/50 [00:15<00:03,  2.63it/s]
 86%|████████▌ | 43/50 [00:16<00:02,  2.63it/s]
 88%|████████▊ | 44/50 [00:16<00:02,  2.63it/s]
 90%|█████████ | 45/50 [00:16<00:01,  2.63it/s]
 92%|█████████▏| 46/50 [00:17<00:01,  2.63it/s]
 94%|█████████▍| 47/50 [00:17<00:01,  2.63it/s]
 96%|█████████▌| 48/50 [00:18<00:00,  2.63it/s]
 98%|█████████▊| 49/50 [00:18<00:00,  2.63it/s]
100%|██████████| 50/50 [00:18<00:00,  2.63it/s]
100%|██████████| 50/50 [00:18<00:00,  2.66it/s]
Running safety checker...
Saving images to file...
Version Details
Version ID
467d062309da518648ba89d226490e02b8ed09b5abc15026e54e31c5a8cd0769
Version Created
January 22, 2024
Run on Replicate →