fermatresearch/flux-controlnet-inpaint 🖼️🔢📝❓✓ → 🖼️

▶️ 35.9K runs 📅 Sep 2024 ⚙️ Cog 0.9.23 🔗 GitHub
controlnet image-editing image-inpainting image-to-image lora

About

Run inpainting with Flux, compatible with Canny ControlNet, LoRAs and HyperFlux_8step

Example Output

Prompt:

"Professional photography of a fox sitting on a bench"

Output

Example output

Performance Metrics

10.94s Prediction Time
91.84s Total Time
All Input Parameters 
{
  "mask": "https://replicate.delivery/pbxt/LdzOC0eYgmiQxsZntL8aUwyQlLjtXQuhmMrXrOUbpMESw11v/output%20%282%29.png",
  "image": "https://replicate.delivery/pbxt/LdzOC2USRj4omEK2igawxoYUPG6hJ2RfRZS2TZXiqSEkybYs/output%20%283%29.png",
  "prompt": "Professional photography of a fox sitting on a bench",
  "strength": 0.8,
  "lora_scale": 0.8,
  "control_image": "https://replicate.delivery/pbxt/LdzOBqGI9FyIIPZOyOBYToYndRLXelYBSqOP1XJlE5Tq5up9/output%20%283%29.png",
  "output_format": "jpg",
  "guidance_scale": 3.5,
  "output_quality": 100,
  "conditioning_scale": 0.5,
  "num_inference_steps": 8,
  "enable_hyper_flux_8_step": true
}
Input Parameters
mask Type: string
The area to inpaint
seed Type: integer
Random seed. Set for reproducible generation
image Type: string
The image to restyle
prompt (required) Type: string
Prompt for generated image
strength Type: numberDefault: 0.8Range: 0 - 1
Img2Img strength
lora_scale Type: numberDefault: 0.8Range: 0 - 1
Scale for the LoRA weights
lora_weights Type: string
Huggingface path, or URL to the LoRA weights. Ex: alvdansen/frosting_lane_flux
control_image Type: string
The image to control the generation
output_format Default: jpg
Format of the output images
guidance_scale Type: numberDefault: 3.5Range: 0 - 30
Guidance scale
output_quality Type: integerDefault: 100Range: 0 - 100
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
conditioning_scale Type: numberDefault: 0.5Range: 0 - 1
ControlNet strength, depth works best at 0.2, canny works best at 0.4. Recommended range is 0.3-0.8
num_inference_steps Type: integerDefault: 8Range: 1 - 28
Number of inference steps
enable_hyper_flux_8_step Type: booleanDefault: true
Whether to use Hyper-FLUX.1-dev-8steps or not. If False, make sure to increase your number of inference steps
Output Schema

Output

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

Example Execution Logs 
Using seed: 28712
  0%|          | 0/7 [00:00<?, ?it/s]
 14%|█▍        | 1/7 [00:00<00:04,  1.37it/s]
 29%|██▊       | 2/7 [00:01<00:03,  1.53it/s]
 43%|████▎     | 3/7 [00:01<00:02,  1.58it/s]
 57%|█████▋    | 4/7 [00:02<00:01,  1.61it/s]
 71%|███████▏  | 5/7 [00:03<00:01,  1.62it/s]
 86%|████████▌ | 6/7 [00:03<00:00,  1.63it/s]
100%|██████████| 7/7 [00:04<00:00,  1.75it/s]
100%|██████████| 7/7 [00:04<00:00,  1.65it/s]
Version Details
Version ID
46ae77d1d148dca1bd61c1215e99ee692c4cf01289a2bba681b14a58c04bda8f
Version Created
September 18, 2024
Run on Replicate →