hazxone/img2img-vg 🔢🖼️❓📝 → 🖼️

▶️ 345 runs 📅 Jul 2023 ⚙️ Cog 0.8.1 📄 Paper
image-style-transfer image-to-image

About

Img2Img diffusion in the style of Van Gogh

Example Output

Prompt:

"lvngvncnt, beautiful woman, highly detailed "

Output

Example output

Performance Metrics

12.19s Prediction Time
12.16s Total Time
All Input Parameters
{
  "image": "https://replicate.delivery/pbxt/JDjlS9i196GEZuR9lSzZJHRVSUcVmTl9NXdEPb5D6Lxs1VF2/vg-2.jpg",
  "width": 512,
  "height": 512,
  "prompt": "lvngvncnt, beautiful woman, highly detailed ",
  "scheduler": "K_EULER",
  "num_outputs": 1,
  "guidance_scale": 6.07,
  "prompt_strength": 0.8,
  "num_inference_steps": 25
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
image (required) Type: string
Inital image to generate variations of.
width Default: 512
Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
height Default: 512
Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
prompt Type: stringDefault: A fantasy landscape, trending on artstation
Input prompt
scheduler Default: DPMSolverMultistep
Choose a scheduler.
num_outputs Type: integerDefault: 1Range: 1 - 8
Number of images to output. Higher number of outputs may OOM.
guidance_scale Type: numberDefault: 7.5Range: 1 - 20
Scale for classifier-free guidance
negative_prompt Type: string
The prompt NOT to guide the image generation. Ignored when not using guidance
prompt_strength Type: numberDefault: 0.8
Prompt strength when providing the image. 1.0 corresponds to full destruction of information in init image
num_inference_steps Type: integerDefault: 25Range: 1 - 500
Number of denoising steps
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 48979
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:09,  2.07it/s]
 10%|█         | 2/20 [00:00<00:09,  2.00it/s]
 15%|█▌        | 3/20 [00:01<00:08,  2.02it/s]
 20%|██        | 4/20 [00:01<00:08,  2.00it/s]
 25%|██▌       | 5/20 [00:02<00:07,  2.01it/s]
 30%|███       | 6/20 [00:03<00:07,  1.99it/s]
 35%|███▌      | 7/20 [00:03<00:06,  2.01it/s]
 40%|████      | 8/20 [00:04<00:06,  1.98it/s]
 45%|████▌     | 9/20 [00:04<00:05,  1.99it/s]
 50%|█████     | 10/20 [00:05<00:05,  1.98it/s]
 55%|█████▌    | 11/20 [00:05<00:04,  1.99it/s]
 60%|██████    | 12/20 [00:06<00:03,  2.00it/s]
 65%|██████▌   | 13/20 [00:06<00:03,  2.00it/s]
 70%|███████   | 14/20 [00:07<00:03,  2.00it/s]
 75%|███████▌  | 15/20 [00:07<00:02,  2.00it/s]
 80%|████████  | 16/20 [00:08<00:02,  2.00it/s]
 85%|████████▌ | 17/20 [00:08<00:01,  2.00it/s]
 90%|█████████ | 18/20 [00:09<00:01,  1.99it/s]
 95%|█████████▌| 19/20 [00:09<00:00,  1.99it/s]
100%|██████████| 20/20 [00:10<00:00,  1.98it/s]
100%|██████████| 20/20 [00:10<00:00,  1.99it/s]
Version Details
Version ID
3edc1fecc293d8c88657d5442ece7857f907bc50b451e0603c7981c240f6a94d
Version Created
July 28, 2023
Run on Replicate →