ai-forever/kandinsky-2-1 🔢❓🖼️📝 → 🖼️

▶️ 85.3K runs 📅 Jun 2023 ⚙️ Cog 0.7.2 🔗 GitHub

image-editing image-to-image text-to-image

About

Kandinsky 2.1 Diffusion Model

Example Output

Prompt:

"A alien cheeseburger creature eating itself, claymation, cinematic, moody lighting"

Output

Performance Metrics

7.83s Prediction Time

7.79s Total Time

All Input Parameters

{
  "task": "text2img",
  "width": 768,
  "height": 768,
  "prompt": "A alien cheeseburger creature eating itself, claymation, cinematic, moody lighting",
  "strength": 0.3,
  "num_outputs": 1,
  "guidance_scale": 1,
  "negative_prompt": "low quality, bad quality",
  "num_steps_prior": 25,
  "num_inference_steps": 100
}

Input Parameters

seed Type: integer: Random seed. Leave blank to randomize the seed
task Default: text2img: Choose a task
image Type: string: Input image for text_guided_img2img task
width Type: integerDefault: 512Range: 128 - 1024: Width of output image. Reduce the seeting if hits memory limits
height Type: integerDefault: 512Range: 128 - 1024: Height of output image. Reduce the seeting if hits memory limits
prompt Type: stringDefault: A alien cheeseburger creature eating itself, claymation, cinematic, moody lighting: Provide input prompt
strength Type: numberDefault: 0.3Range: 0 - 1: indicates how much to transform the input iamge, valid for text_guided_img2img task.
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of images to output.
guidance_scale Type: numberDefault: 4Range: 1 - 20: Scale for classifier-free guidance
negative_prompt Type: stringDefault: low quality, bad quality: Specify things to not see in the output for text2img and text_guided_img2img tasks
num_steps_prior Type: integerDefault: 25Range: 1 - 500: Number of denoising steps in prior
num_inference_steps Type: integerDefault: 100Range: 1 - 500: Number of denoising steps

Output Schema

Output

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

Example Execution Logs

Using seed: 9578
  0%|          | 0/25 [00:00<?, ?it/s]
 20%|██        | 5/25 [00:00<00:00, 45.87it/s]
 40%|████      | 10/25 [00:00<00:00, 46.46it/s]
 60%|██████    | 15/25 [00:00<00:00, 44.90it/s]
 80%|████████  | 20/25 [00:00<00:00, 46.28it/s]
100%|██████████| 25/25 [00:00<00:00, 47.07it/s]
100%|██████████| 25/25 [00:00<00:00, 46.49it/s]
  0%|          | 0/100 [00:00<?, ?it/s]
  2%|▏         | 2/100 [00:00<00:06, 15.23it/s]
  4%|▍         | 4/100 [00:00<00:06, 15.72it/s]
  6%|▌         | 6/100 [00:00<00:05, 16.19it/s]
  8%|▊         | 8/100 [00:00<00:05, 16.23it/s]
 10%|█         | 10/100 [00:00<00:05, 16.41it/s]
 12%|█▏        | 12/100 [00:00<00:05, 16.39it/s]
 14%|█▍        | 14/100 [00:00<00:05, 16.24it/s]
 16%|█▌        | 16/100 [00:00<00:05, 16.33it/s]
 18%|█▊        | 18/100 [00:01<00:05, 16.17it/s]
 20%|██        | 20/100 [00:01<00:04, 16.32it/s]
 22%|██▏       | 22/100 [00:01<00:04, 16.41it/s]
 24%|██▍       | 24/100 [00:01<00:04, 16.50it/s]
 26%|██▌       | 26/100 [00:01<00:04, 16.57it/s]
 28%|██▊       | 28/100 [00:01<00:04, 16.57it/s]
 30%|███       | 30/100 [00:01<00:04, 16.53it/s]
 32%|███▏      | 32/100 [00:01<00:04, 16.60it/s]
 34%|███▍      | 34/100 [00:02<00:04, 16.42it/s]
 36%|███▌      | 36/100 [00:02<00:03, 16.50it/s]
 38%|███▊      | 38/100 [00:02<00:03, 16.48it/s]
 40%|████      | 40/100 [00:02<00:03, 16.51it/s]
 42%|████▏     | 42/100 [00:02<00:03, 16.55it/s]
 44%|████▍     | 44/100 [00:02<00:03, 16.48it/s]
 46%|████▌     | 46/100 [00:02<00:03, 16.49it/s]
 48%|████▊     | 48/100 [00:02<00:03, 16.54it/s]
 50%|█████     | 50/100 [00:03<00:03, 16.43it/s]
 52%|█████▏    | 52/100 [00:03<00:02, 16.45it/s]
 54%|█████▍    | 54/100 [00:03<00:02, 16.34it/s]
 56%|█████▌    | 56/100 [00:03<00:02, 16.40it/s]
 58%|█████▊    | 58/100 [00:03<00:02, 16.42it/s]
 60%|██████    | 60/100 [00:03<00:02, 16.48it/s]
 62%|██████▏   | 62/100 [00:03<00:02, 16.49it/s]
 64%|██████▍   | 64/100 [00:03<00:02, 16.51it/s]
 66%|██████▌   | 66/100 [00:04<00:02, 16.48it/s]
 68%|██████▊   | 68/100 [00:04<00:01, 16.40it/s]
 70%|███████   | 70/100 [00:04<00:01, 16.45it/s]
 72%|███████▏  | 72/100 [00:04<00:01, 16.55it/s]
 74%|███████▍  | 74/100 [00:04<00:01, 16.63it/s]
 76%|███████▌  | 76/100 [00:04<00:01, 16.70it/s]
 78%|███████▊  | 78/100 [00:04<00:01, 16.60it/s]
 80%|████████  | 80/100 [00:04<00:01, 16.59it/s]
 82%|████████▏ | 82/100 [00:04<00:01, 16.69it/s]
 84%|████████▍ | 84/100 [00:05<00:00, 16.68it/s]
 86%|████████▌ | 86/100 [00:05<00:00, 16.74it/s]
 88%|████████▊ | 88/100 [00:05<00:00, 16.77it/s]
 90%|█████████ | 90/100 [00:05<00:00, 16.46it/s]
 92%|█████████▏| 92/100 [00:05<00:00, 16.58it/s]
 94%|█████████▍| 94/100 [00:05<00:00, 16.55it/s]
 96%|█████████▌| 96/100 [00:05<00:00, 16.65it/s]
 98%|█████████▊| 98/100 [00:05<00:00, 16.67it/s]
100%|██████████| 100/100 [00:06<00:00, 16.63it/s]
100%|██████████| 100/100 [00:06<00:00, 16.49it/s]

Version Details

Version ID: a768f3c2e174c54b576cc4f222e789e161160403d0cd0ace41eeb9a0f8c8d5f8
Version Created: June 9, 2023

Run on Replicate →