cjwbw/blipdiffusion-controlnet 🔢📝🖼️❓ → 🖼️

▶️ 188 runs 📅 Feb 2024 ⚙️ Cog 0.9.4 📄 Paper ⚖️ License
controlnet image-style-transfer image-to-image

About

Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing with ControlNet

Example Output

Prompt:

"on a marble table"

Output

Example output

Performance Metrics

3.04s Prediction Time
3.11s Total Time
All Input Parameters 
{
  "seed": 10,
  "prompt": "on a marble table",
  "style_image": "https://replicate.delivery/pbxt/KNc7eIC5UqBH5GxAUu3i5WWgQooBWg1WQmKlZyFczvaftVw5/flower.jpg",
  "guidance_scale": 7.5,
  "controlnet_type": "canny",
  "negative_prompt": "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry",
  "condtioning_image": "https://replicate.delivery/pbxt/KNc7dtQmRYksrDn4eC1qGrtlBJIkHHmk4S7OSMT8UAYMHRul/kettle.jpg",
  "num_inference_steps": 25,
  "style_subject_category": "flower",
  "target_subject_category": "teapot"
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
prompt Type: stringDefault: on a marble table
The prompt to guide the image generation.
style_image (required) Type: string
The reference style image to condition the generation on.
guidance_scale Type: numberDefault: 7.5Range: 1 - 20
Scale for classifier-free guidance.
controlnet_type Default: canny
Choose a control net
negative_prompt Type: stringDefault: over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, ugly, bad anatomy, bad proportions, deformed, blurry
The prompt or prompts not to guide the image generation.
condtioning_image (required) Type: string
The conditioning canny edge image to condition the generation on.
num_inference_steps Type: integerDefault: 25Range: 1 - 500
The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
style_subject_category Type: stringDefault: flower
The source subject category (subject that defines the style).
target_subject_category Type: stringDefault: teapot
The target subject category (subject to geenrate).
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Using seed: 10
  0%|          | 0/26 [00:00<?, ?it/s]
  8%|▊         | 2/26 [00:00<00:01, 19.88it/s]
 15%|█▌        | 4/26 [00:00<00:01, 18.13it/s]
 23%|██▎       | 6/26 [00:00<00:01, 17.66it/s]
 31%|███       | 8/26 [00:00<00:01, 17.46it/s]
 38%|███▊      | 10/26 [00:00<00:00, 17.34it/s]
 46%|████▌     | 12/26 [00:00<00:00, 17.29it/s]
 54%|█████▍    | 14/26 [00:00<00:00, 17.27it/s]
 62%|██████▏   | 16/26 [00:00<00:00, 17.23it/s]
 69%|██████▉   | 18/26 [00:01<00:00, 17.18it/s]
 77%|███████▋  | 20/26 [00:01<00:00, 17.16it/s]
 85%|████████▍ | 22/26 [00:01<00:00, 17.17it/s]
 92%|█████████▏| 24/26 [00:01<00:00, 17.16it/s]
100%|██████████| 26/26 [00:01<00:00, 17.16it/s]
100%|██████████| 26/26 [00:01<00:00, 17.33it/s]
Version Details
Version ID
0072c227cdc7eea6c41411b54655b874faac1a7b8288386dc2a3c677c6faa403
Version Created
February 10, 2024
Run on Replicate →