cjwbw/kandinsky-2-2-controlnet-depth 🔢❓🖼️📝 → 🖼️

▶️ 3.8K runs 📅 Jul 2023 ⚙️ Cog 0.8.1 🔗 GitHub ⚖️ License

controlnet image-to-image text-to-image

About

Kandinsky Image Generation with ControlNet Conditioning

Example Output

Prompt:

"A robot, 4k photo"

Output

Performance Metrics

9.33s Prediction Time

284.38s Total Time

All Input Parameters

{
  "task": "img2img",
  "image": "https://replicate.delivery/pbxt/JBQjVyAYINXgKMvXGfE2ykyLgNE6E7ytZLC8b26BM2D0IRoG/cat.png",
  "width": 768,
  "height": 768,
  "prompt": "A robot, 4k photo",
  "num_outputs": 1,
  "negative_prompt": "lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, username, watermark, signature",
  "num_inference_steps": 75
}

Input Parameters

seed Type: integer: Random seed. Leave blank to randomize the seed
task Default: img2img: Choose a task
image Type: string: Input image
width Default: 768: Width of output image. Lower the setting if hits memory limits.
height Default: 768: Height of output image. Lower the setting if hits memory limits.
prompt Type: stringDefault: A robot, 4k photo: Input prompt
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of images to output.
negative_prompt Type: stringDefault: lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, username, watermark, signature: Specify things to not see in the output
num_inference_steps Type: integerDefault: 75Range: 1 - 500: Number of denoising steps

Output Schema

Output

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

Example Execution Logs

Using seed: 49968
  0%|          | 0/21 [00:00<?, ?it/s]
 19%|█▉        | 4/21 [00:00<00:00, 39.59it/s]
 43%|████▎     | 9/21 [00:00<00:00, 40.19it/s]
 67%|██████▋   | 14/21 [00:00<00:00, 40.28it/s]
 90%|█████████ | 19/21 [00:00<00:00, 40.10it/s]
100%|██████████| 21/21 [00:00<00:00, 40.17it/s]
Token indices sequence length is longer than the specified maximum sequence length for this model (112 > 77). Running this sequence through the model will result in indexing errors
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, username, watermark, signature']
  0%|          | 0/25 [00:00<?, ?it/s]
 20%|██        | 5/25 [00:00<00:00, 40.73it/s]
 40%|████      | 10/25 [00:00<00:00, 39.75it/s]
 60%|██████    | 15/25 [00:00<00:00, 39.91it/s]
 80%|████████  | 20/25 [00:00<00:00, 39.96it/s]
 96%|█████████▌| 24/25 [00:00<00:00, 39.72it/s]
100%|██████████| 25/25 [00:00<00:00, 39.86it/s]
  0%|          | 0/37 [00:00<?, ?it/s]
  3%|▎         | 1/37 [00:00<00:09,  3.78it/s]
  8%|▊         | 3/37 [00:00<00:04,  8.39it/s]
 14%|█▎        | 5/37 [00:00<00:02, 10.77it/s]
 19%|█▉        | 7/37 [00:00<00:02, 12.40it/s]
 24%|██▍       | 9/37 [00:00<00:02, 13.46it/s]
 30%|██▉       | 11/37 [00:00<00:01, 14.10it/s]
 35%|███▌      | 13/37 [00:01<00:01, 14.55it/s]
 41%|████      | 15/37 [00:01<00:01, 14.79it/s]
 46%|████▌     | 17/37 [00:01<00:01, 15.03it/s]
 51%|█████▏    | 19/37 [00:01<00:01, 15.20it/s]
 57%|█████▋    | 21/37 [00:01<00:01, 15.28it/s]
 62%|██████▏   | 23/37 [00:01<00:00, 15.37it/s]
 68%|██████▊   | 25/37 [00:01<00:00, 15.45it/s]
 73%|███████▎  | 27/37 [00:01<00:00, 15.53it/s]
 78%|███████▊  | 29/37 [00:02<00:00, 15.62it/s]
 84%|████████▍ | 31/37 [00:02<00:00, 15.39it/s]
 89%|████████▉ | 33/37 [00:02<00:00, 15.50it/s]
 95%|█████████▍| 35/37 [00:02<00:00, 15.63it/s]
100%|██████████| 37/37 [00:02<00:00, 15.70it/s]
100%|██████████| 37/37 [00:02<00:00, 14.28it/s]

Version Details

Version ID: 98b54ca0b42be225e927f1dae2d9c506e69fe5b3bce301e13718d662a227a12b
Version Created: July 16, 2023

Run on Replicate →