lucataco/sdxl-deepcache 🖼️🔢📝❓✓ → 🖼️

▶️ 3.9K runs 📅 Jan 2024 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License
image-inpainting image-to-image text-to-image

About

SDXL using DeepCache

Example Output

Prompt:

"black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed"

Output

Example output

Performance Metrics

3.10s Prediction Time
3.11s Total Time
All Input Parameters 
{
  "width": 1024,
  "height": 1024,
  "prompt": "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed",
  "scheduler": "KarrasDPM",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "negative_prompt": "worst quality, low quality",
  "prompt_strength": 0.8,
  "enable_deepcache": true,
  "num_inference_steps": 25
}
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
height Type: integerDefault: 1024
Height of output image
prompt Type: stringDefault: black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed
Input prompt
scheduler Default: KarrasDPM
scheduler
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to output.
guidance_scale Type: numberDefault: 7.5Range: 1 - 50
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: worst quality, low quality
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
enable_deepcache Type: booleanDefault: true
Enable DeepCache
num_inference_steps Type: integerDefault: 25Range: 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: 2749139505
Prompt: black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed
txt2img mode
  0%|          | 0/25 [00:00<?, ?it/s]
  4%|▍         | 1/25 [00:00<00:03,  7.27it/s]
 16%|█▌        | 4/25 [00:00<00:01, 15.67it/s]
 28%|██▊       | 7/25 [00:00<00:01, 17.97it/s]
 40%|████      | 10/25 [00:00<00:00, 19.05it/s]
 52%|█████▏    | 13/25 [00:00<00:00, 19.54it/s]
 64%|██████▍   | 16/25 [00:00<00:00, 19.58it/s]
 76%|███████▌  | 19/25 [00:01<00:00, 19.90it/s]
 88%|████████▊ | 22/25 [00:01<00:00, 20.14it/s]
100%|██████████| 25/25 [00:01<00:00, 20.18it/s]
100%|██████████| 25/25 [00:01<00:00, 19.12it/s]
Inference took:  1.8965418338775635
Version Details
Version ID
eaf678fb34006669e9a3c6dd5971e2279bf20ee0adeced464d7b6d95de16dc93
Version Created
January 7, 2024
Run on Replicate →