chenxwh/ominicontrol-subject 🔢🖼️❓📝 → 🖼️

▶️ 2.1K runs 📅 Dec 2024 ⚙️ Cog 0.9.23 🔗 GitHub 📄 Paper ⚖️ License

image-consistant-object-generation image-consistent-character-generation image-to-image

About

Minimal and Universal Control for Diffusion Transformer - demo for Subject-driven generation

Example Output

Prompt:

"On Christmas evening, on a crowded sidewalk, this item sits on the road, covered in snow and wearing a Christmas hat."

Output

Performance Metrics

15.58s Prediction Time

124.46s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/MF5rBXkFkj5E0LhAU7kT6ADRBtTwQYouMqPenUpTZocf8BuB/penguin.jpg",
  "model": "subject",
  "prompt": "On Christmas evening, on a crowded sidewalk, this item sits on the road, covered in snow and wearing a Christmas hat.",
  "guidance_scale": 7.5,
  "num_inference_steps": 50
}

Input Parameters

seed Type: integer: Random seed. Leave blank to randomize the seed
image (required) Type: string: Input image
model Default: subject: Choose a task
prompt Type: stringDefault: On Christmas evening, on a crowded sidewalk, this item sits on the road, covered in snow and wearing a Christmas hat.: Input prompt.
guidance_scale Type: numberDefault: 7.5Range: 1 - 20: Scale for classifier-free guidance
num_inference_steps Type: integerDefault: 50Range: 1 - 500: Number of denoising steps

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Using seed: 43522
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:15,  3.06it/s]
  4%|▍         | 2/50 [00:00<00:13,  3.51it/s]
  6%|▌         | 3/50 [00:00<00:13,  3.45it/s]
  8%|▊         | 4/50 [00:01<00:13,  3.42it/s]
 10%|█         | 5/50 [00:01<00:13,  3.41it/s]
 12%|█▏        | 6/50 [00:01<00:12,  3.40it/s]
 14%|█▍        | 7/50 [00:02<00:12,  3.39it/s]
 16%|█▌        | 8/50 [00:02<00:12,  3.39it/s]
 18%|█▊        | 9/50 [00:02<00:12,  3.39it/s]
 20%|██        | 10/50 [00:02<00:11,  3.39it/s]
 22%|██▏       | 11/50 [00:03<00:11,  3.39it/s]
 24%|██▍       | 12/50 [00:03<00:11,  3.38it/s]
 26%|██▌       | 13/50 [00:03<00:10,  3.38it/s]
 28%|██▊       | 14/50 [00:04<00:10,  3.38it/s]
 30%|███       | 15/50 [00:04<00:10,  3.38it/s]
 32%|███▏      | 16/50 [00:04<00:10,  3.38it/s]
 34%|███▍      | 17/50 [00:05<00:09,  3.38it/s]
 36%|███▌      | 18/50 [00:05<00:09,  3.38it/s]
 38%|███▊      | 19/50 [00:05<00:09,  3.38it/s]
 40%|████      | 20/50 [00:05<00:08,  3.38it/s]
 42%|████▏     | 21/50 [00:06<00:08,  3.38it/s]
 44%|████▍     | 22/50 [00:06<00:08,  3.38it/s]
 46%|████▌     | 23/50 [00:06<00:07,  3.38it/s]
 48%|████▊     | 24/50 [00:07<00:07,  3.38it/s]
 50%|█████     | 25/50 [00:07<00:07,  3.38it/s]
 52%|█████▏    | 26/50 [00:07<00:07,  3.38it/s]
 54%|█████▍    | 27/50 [00:07<00:06,  3.37it/s]
 56%|█████▌    | 28/50 [00:08<00:06,  3.37it/s]
 58%|█████▊    | 29/50 [00:08<00:06,  3.38it/s]
 60%|██████    | 30/50 [00:08<00:05,  3.38it/s]
 62%|██████▏   | 31/50 [00:09<00:05,  3.37it/s]
 64%|██████▍   | 32/50 [00:09<00:05,  3.37it/s]
 66%|██████▌   | 33/50 [00:09<00:05,  3.38it/s]
 68%|██████▊   | 34/50 [00:10<00:04,  3.38it/s]
 70%|███████   | 35/50 [00:10<00:04,  3.37it/s]
 72%|███████▏  | 36/50 [00:10<00:04,  3.37it/s]
 74%|███████▍  | 37/50 [00:10<00:03,  3.37it/s]
 76%|███████▌  | 38/50 [00:11<00:03,  3.37it/s]
 78%|███████▊  | 39/50 [00:11<00:03,  3.37it/s]
 80%|████████  | 40/50 [00:11<00:02,  3.37it/s]
 82%|████████▏ | 41/50 [00:12<00:02,  3.37it/s]
 84%|████████▍ | 42/50 [00:12<00:02,  3.37it/s]
 86%|████████▌ | 43/50 [00:12<00:02,  3.37it/s]
 88%|████████▊ | 44/50 [00:13<00:01,  3.37it/s]
 90%|█████████ | 45/50 [00:13<00:01,  3.37it/s]
 92%|█████████▏| 46/50 [00:13<00:01,  3.37it/s]
 94%|█████████▍| 47/50 [00:13<00:00,  3.37it/s]
 96%|█████████▌| 48/50 [00:14<00:00,  3.37it/s]
 98%|█████████▊| 49/50 [00:14<00:00,  3.37it/s]
100%|██████████| 50/50 [00:14<00:00,  3.37it/s]
100%|██████████| 50/50 [00:14<00:00,  3.38it/s]

Version Details

Version ID: 65f9489081d0f94bb3085b5a5df2758501c8620d6cb5e0b5874e8f48ba5e9cdb
Version Created: December 31, 2024

Run on Replicate →