datacte/proteus-v0.4-lightning 🖼️🔢📝❓✓ → 🖼️

▶️ 132.0K runs 📅 Feb 2024 ⚙️ Cog 0.9.3 🔗 GitHub ⚖️ License
image-inpainting image-to-image text-to-image

About

ProteusV0.4: The Style Update - enhances stylistic capabilities, similar to Midjourney's approach, rather than advancing prompt comprehension

Example Output

Prompt:

"3 fish in a fish tank wearing adorable outfits, best quality, hd"

Output

Example output

Performance Metrics

2.66s Prediction Time
2.66s Total Time
All Input Parameters 
{
  "width": 1024,
  "height": 1024,
  "prompt": "3 fish in a fish tank wearing adorable outfits, best quality, hd",
  "scheduler": "K_EULER_ANCESTRAL",
  "num_outputs": 1,
  "guidance_scale": 2,
  "apply_watermark": true,
  "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image",
  "prompt_strength": 0.8,
  "num_inference_steps": 8
}
Input Parameters
mask Type: string
Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
seed Type: integer
Random seed. Leave blank to randomize the seed
image Type: string
Input image for img2img or inpaint mode
width Type: integerDefault: 1024
Width of output image. Recommended 1024 or 1280
height Type: integerDefault: 1024
Height of output image. Recommended 1024 or 1280
prompt Type: stringDefault: 3 fish in a fish tank wearing adorable outfits, best quality, hd
Input prompt
scheduler Default: K_EULER_ANCESTRAL
scheduler
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to output.
guidance_scale Type: numberDefault: 2Range: 0 - 10
Scale for classifier-free guidance
apply_watermark Type: booleanDefault: true
Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
negative_prompt Type: stringDefault: nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image
Negative Input prompt
prompt_strength Type: numberDefault: 0.8Range: 0 - 1
Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
num_inference_steps Type: integerDefault: 8Range: 1 - 100
Number of denoising steps
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety
Output Schema

Output

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

Example Execution Logs 
Using seed: 2206289182
Prompt: 3 fish in a fish tank wearing adorable outfits, best quality, hd
txt2img mode
  0%|          | 0/8 [00:00<?, ?it/s]
 25%|██▌       | 2/8 [00:00<00:00,  6.78it/s]
 38%|███▊      | 3/8 [00:00<00:00,  5.88it/s]
 50%|█████     | 4/8 [00:00<00:00,  5.49it/s]
 62%|██████▎   | 5/8 [00:00<00:00,  5.28it/s]
 75%|███████▌  | 6/8 [00:01<00:00,  5.15it/s]
 88%|████████▊ | 7/8 [00:01<00:00,  5.08it/s]
100%|██████████| 8/8 [00:01<00:00,  5.04it/s]
100%|██████████| 8/8 [00:01<00:00,  5.30it/s]
Version Details
Version ID
21464a198e9baa3b583f93d8daaaa9e851b91ae1e32accb96ce5081a18a2d87c
Version Created
February 22, 2024
Run on Replicate →