fofr/kolors 🔢📝❓ → 🖼️

▶️ 36.4K runs 📅 Jul 2024 ⚙️ Cog 0.9.13 🔗 GitHub 📄 Paper ⚖️ License
multilingual text-rendering text-to-image

About

A large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team

Example Output

Prompt:

"a kingfisher saying "hello" in a speech bubble"

Output

Example output

Performance Metrics

5.86s Prediction Time
5.87s Total Time
All Input Parameters 
{
  "cfg": 5,
  "steps": 25,
  "width": 1024,
  "height": 1024,
  "prompt": "a kingfisher saying \"hello\" in a speech bubble",
  "scheduler": "EulerDiscreteScheduler",
  "output_format": "webp",
  "output_quality": 80,
  "negative_prompt": "",
  "number_of_images": 1
}
Input Parameters
cfg Type: numberDefault: 5Range: 0 - 20
Guidance scale
seed Type: integer
Set a seed for reproducibility. Random by default.
steps Type: integerDefault: 25Range: 1 - 50
Number of inference steps
width Type: integerDefault: 1024Range: 512 - 2048
Width of the image
height Type: integerDefault: 1024Range: 512 - 2048
Height of the image
prompt Type: stringDefault:
scheduler Default: EulerDiscreteScheduler
Scheduler
output_format Default: webp
Format of the output images
output_quality Type: integerDefault: 80Range: 0 - 100
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.
negative_prompt Type: stringDefault:
Things you do not want to see in your image
number_of_images Type: integerDefault: 1Range: 1 - 10
Number of images to generate
Output Schema

Output

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

Example Execution Logs 
Random seed set to: 2209112854
Running workflow
got prompt
Executing node 2, title: Kolors Sampler, class type: KolorsSampler
  0%|          | 0/25 [00:00<?, ?it/s]
  8%|▊         | 2/25 [00:00<00:03,  7.09it/s]
 12%|█▏        | 3/25 [00:00<00:03,  6.17it/s]
 16%|█▌        | 4/25 [00:00<00:03,  5.76it/s]
 20%|██        | 5/25 [00:00<00:03,  5.55it/s]
 24%|██▍       | 6/25 [00:01<00:03,  5.40it/s]
 28%|██▊       | 7/25 [00:01<00:03,  5.32it/s]
 32%|███▏      | 8/25 [00:01<00:03,  5.27it/s]
 36%|███▌      | 9/25 [00:01<00:03,  5.24it/s]
 40%|████      | 10/25 [00:01<00:02,  5.22it/s]
 44%|████▍     | 11/25 [00:02<00:02,  5.19it/s]
 48%|████▊     | 12/25 [00:02<00:02,  5.18it/s]
 52%|█████▏    | 13/25 [00:02<00:02,  5.17it/s]
 56%|█████▌    | 14/25 [00:02<00:02,  5.17it/s]
 60%|██████    | 15/25 [00:02<00:01,  5.17it/s]
 64%|██████▍   | 16/25 [00:02<00:01,  5.16it/s]
 68%|██████▊   | 17/25 [00:03<00:01,  5.15it/s]
 72%|███████▏  | 18/25 [00:03<00:01,  5.15it/s]
 76%|███████▌  | 19/25 [00:03<00:01,  5.15it/s]
 80%|████████  | 20/25 [00:03<00:00,  5.15it/s]
 84%|████████▍ | 21/25 [00:03<00:00,  5.15it/s]
 88%|████████▊ | 22/25 [00:04<00:00,  5.15it/s]
 92%|█████████▏| 23/25 [00:04<00:00,  5.15it/s]
 96%|█████████▌| 24/25 [00:04<00:00,  5.15it/s]
100%|██████████| 25/25 [00:04<00:00,  5.15it/s]
100%|██████████| 25/25 [00:04<00:00,  5.27it/s]
Executing node 7, title: VAE Decode, class type: VAEDecode
Executing node 9, title: Save Image, class type: SaveImage
Prompt executed in 5.38 seconds
outputs:  {'9': {'images': [{'filename': 'R8_Kolor_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
R8_Kolor_00001_.png
Version Details
Version ID
6145c9c5cbd646873232d661fe0398ab87ac93db66d5c365959a471c651862d7
Version Created
July 18, 2024
Run on Replicate →