adalab-ai/kandinsky_v2_2 🔢❓🖼️📝 → 🖼️

▶️ 44.3K runs 📅 Jul 2023 ⚙️ Cog 0.7.2 🔗 GitHub ⚖️ License

image-to-image text-to-image

About

Generate images with Kandinsky 2.2 - Mix text and images

Example Output

Prompt:

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

Output

Performance Metrics

3.25s Prediction Time

3.21s Total Time

All Input Parameters

{
  "task": "text2img",
  "width": 1024,
  "height": 1024,
  "prompt": "A alien cheeseburger creature eating itself, claymation, cinematic, moody lighting",
  "scheduler": "unipc",
  "img_weight": 1,
  "num_outputs": 1,
  "guidance_scale": 4,
  "negative_prompt": "ugly, tiling, oversaturated, undersaturated, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, watermark, grainy, signature, cut off, draft",
  "num_steps_prior": 2,
  "num_inference_steps": 18
}

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 text2img
width Type: integerDefault: 512Range: 64 - 1024: Width of output image. Reduce the seeting if hits memory limits
height Type: integerDefault: 512Range: 64 - 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
scheduler Default: unipc: Choose a scheduler
img_weight Type: numberDefault: 1Range: 0 - 10: Weight of image - larger than 1 means more weight to image, lower than 0 is more weight to text
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of images to output.
guidance_scale Type: numberDefault: 4Range: 1 - 10: Scale for classifier-free guidance
negative_prompt Type: stringDefault: ugly, tiling, oversaturated, undersaturated, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, watermark, grainy, signature, cut off, draft: Specify things to not see in the output for text2img and text_guided_img2img tasks
num_steps_prior Type: integerDefault: 2Range: 1 - 500: Number of denoising steps in prior
num_inference_steps Type: integerDefault: 18Range: 1 - 500: Number of denoising steps

Output Schema

Output

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

Example Execution Logs

Using seed: 47117
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 44.94it/s]
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 45.88it/s]
  0%|          | 0/18 [00:00<?, ?it/s]
  6%|▌         | 1/18 [00:00<00:02,  6.39it/s]
 17%|█▋        | 3/18 [00:00<00:01,  9.28it/s]
 28%|██▊       | 5/18 [00:00<00:01, 10.58it/s]
 39%|███▉      | 7/18 [00:00<00:00, 11.20it/s]
 50%|█████     | 9/18 [00:00<00:00, 11.55it/s]
 61%|██████    | 11/18 [00:00<00:00, 11.76it/s]
 72%|███████▏  | 13/18 [00:01<00:00, 11.89it/s]
 83%|████████▎ | 15/18 [00:01<00:00, 11.96it/s]
 94%|█████████▍| 17/18 [00:01<00:00, 12.01it/s]
100%|██████████| 18/18 [00:01<00:00, 11.45it/s]

Version Details

Version ID: eb68c00d7fc7d7297a04dcecbdd29032361ab8f1d3f6843c32fbd6ec70532319
Version Created: July 18, 2023

Run on Replicate →