cjwbw/pixart-sigma 🔢📝 → 🖼️

▶️ 6.7K runs 📅 Apr 2024 ⚙️ Cog 0.9.4 🔗 GitHub 📄 Paper ⚖️ License
4k high-resolution text-to-image

About

Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Example Output

Prompt:

"Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee."

Output

Example output

Performance Metrics

24.97s Prediction Time
25.02s Total Time
All Input Parameters 
{
  "prompt": "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee.",
  "guidance_scale": 4.5,
  "num_inference_steps": 20
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
width Type: integerDefault: 1024
Width of output image
height Type: integerDefault: 1024
Height of output image
prompt Type: stringDefault: A small cactus with a happy face in the Sahara desert.
Input prompt
guidance_scale Type: numberDefault: 4.5Range: 1 - 20
Scale for classifier-free guidance
negative_prompt Type: stringDefault:
Specify things to not see in the output
num_inference_steps Type: integerDefault: 20Range: 1 - 500
Number of denoising steps
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Using seed: 20940
Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:
`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.
Setting `clean_caption` to False...
Setting `clean_caption=True` requires the Beautiful Soup library but it was not found in your environment. You can install it with pip:
`pip install beautifulsoup4`. Please note that you may need to restart your runtime after installation.
Setting `clean_caption` to False...
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:01<00:21,  1.13s/it]
 10%|█         | 2/20 [00:02<00:20,  1.11s/it]
 15%|█▌        | 3/20 [00:03<00:18,  1.12s/it]
 20%|██        | 4/20 [00:04<00:17,  1.12s/it]
 25%|██▌       | 5/20 [00:05<00:16,  1.12s/it]
 30%|███       | 6/20 [00:06<00:15,  1.12s/it]
 35%|███▌      | 7/20 [00:07<00:14,  1.12s/it]
 40%|████      | 8/20 [00:08<00:13,  1.12s/it]
 45%|████▌     | 9/20 [00:10<00:12,  1.12s/it]
 50%|█████     | 10/20 [00:11<00:11,  1.12s/it]
 55%|█████▌    | 11/20 [00:12<00:10,  1.12s/it]
 60%|██████    | 12/20 [00:13<00:08,  1.12s/it]
 65%|██████▌   | 13/20 [00:14<00:07,  1.12s/it]
 70%|███████   | 14/20 [00:15<00:06,  1.12s/it]
 75%|███████▌  | 15/20 [00:16<00:05,  1.12s/it]
 80%|████████  | 16/20 [00:17<00:04,  1.12s/it]
 85%|████████▌ | 17/20 [00:19<00:03,  1.12s/it]
 90%|█████████ | 18/20 [00:20<00:02,  1.12s/it]
 95%|█████████▌| 19/20 [00:21<00:01,  1.12s/it]
100%|██████████| 20/20 [00:22<00:00,  1.12s/it]
100%|██████████| 20/20 [00:22<00:00,  1.12s/it]
Version Details
Version ID
5a54352c99d9fef467986bc8f3a20205e8712cbd3df1cbae4975d6254c902de1
Version Created
April 13, 2024
Run on Replicate →