cjwbw/blipdiffusion 🔢📝🖼️ → 🖼️

▶️ 356 runs 📅 Feb 2024 ⚙️ Cog 0.9.4 📄 Paper ⚖️ License
image-consistent-character-generation image-editing image-to-image

About

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

Example Output

Prompt:

"painting by Van Gogh"

Output

Example output

Performance Metrics

3.30s Prediction Time
98.66s Total Time
All Input Parameters 
{
  "width": 512,
  "height": 512,
  "prompt": "painting by Van Gogh",
  "guidance_scale": 7.5,
  "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",
  "reference_image": "https://replicate.delivery/pbxt/KNZcJhVZuWiMWYReUDO2J0Up9CrBN7NmubFg2ZHADbJ5tP9c/dog.png",
  "num_inference_steps": 25,
  "source_subject_category": "dog",
  "target_subject_category": "dog"
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
prompt Type: stringDefault: swimming underwater
The prompt to guide the image generation.
guidance_scale Type: numberDefault: 7.5Range: 1 - 20
Scale for classifier-free guidance.
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.
reference_image (required) Type: string
The reference 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.
source_subject_category Type: stringDefault: dog
The source subject category.
target_subject_category Type: stringDefault: dog
The target subject category.
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:00<00:03,  7.75it/s]
 15%|█▌        | 4/26 [00:00<00:01, 18.80it/s]
 27%|██▋       | 7/26 [00:00<00:00, 21.42it/s]
 38%|███▊      | 10/26 [00:00<00:00, 22.74it/s]
 50%|█████     | 13/26 [00:00<00:00, 23.47it/s]
 62%|██████▏   | 16/26 [00:00<00:00, 23.89it/s]
 73%|███████▎  | 19/26 [00:00<00:00, 24.06it/s]
 85%|████████▍ | 22/26 [00:00<00:00, 24.28it/s]
 96%|█████████▌| 25/26 [00:01<00:00, 24.07it/s]
100%|██████████| 26/26 [00:01<00:00, 22.92it/s]
Version Details
Version ID
81a70441392af1288983861c01b09317acfc5eb5ba1343e86a2578487b26620f
Version Created
February 10, 2024
Run on Replicate →