Since CivitAI is going down THE DRAIN
I won't be updating this workflow here anymore, and I won't post any more models from now on.
I hope to find interest from people to keep updating this. Thanks everyone!
Keep following this workflow development and more on my new Discord server: https://discord.gg/EwKE8KBDqD
Get new releases from GitHub: https://github.com/diodiogod/Comfy-Inpainting-Works
Now there is a "simple/compact" version that I will update together with the normal one.
Read "about this model" on the right panel please!! I recommend reading v6.0, v5.0, v5.1 as well.
This is a proper inpainting with alimama control-net + Flux Fill + Flux Tools (Depth an Canny) support from V7 and above.
I try my best to avoid hiding the workflow flow, while balancing keeping it clean and user-friendly.
This workflow will make sure your image is composited in the end to prevent VAE degradation AND from v5 will make sure your image is a multiple of 8 (so it doesn't get resized by ksampler) at the same time it avoids resizing at all (unless you want to) since resizing will degrade the original image as well.
For inpainting that leaves a face and changes the whole background and character, Alimama works way better. Alimama also works better for LoRas. Alimama is terrible at outpainting and Flux Fill is amazing. You should test both. My comfyUI OOM or crashes when switching from one to the other IF my system memory page file is not large enough. With a pagefile of 50GB I can freely switch from Flux Fill to normal Flux Dev now.
It does use a lot of custom nodes to make life easier and workflow cleaner. Use manager to install the missing ones.
Supports loading of an external mask (need to match the image size) or doing the inpainting within the right-click "Open MaskEditor" on the image itself.
Supports FILL -the normal fill, like Auto1111- (use FastBypasser - black node)
Supports area inpaiting x full image inpaiting (use FastBypasser - black node)
Supports variable denoise (Change denoise on the CONTROL ROOM)
Supports Negative (use FastBypasser - black node)
Proper composite so no VAE degradation
Support for Flux Tools (Depth an Canny) with Alimama
I added LoRa support and Daemon Detailer support (both are optional)
Description
v7.0 Video: https://youtu.be/cPg49GoHpSI
🔹 New: Flux Tools LoRA Depth and Canny "control-net" support
(Works with Alimama — ❗❗ it will NOT work Flux Fill ❗❗
❗ a) Add new group for Loading each LoRA model.
• They should be loaded all the time and will be dynamically used.
• You can control each LoRA strength — recommended: 0.75
❗ b) New toggles on the control-room group:
• Choose between Depth OR Canny (not both)
❗ c) Depth and LoRA groups for LoRA InstructPixToPixConditioning:
• Allows you to choose when Depth or Canny will start and stop
• Conditioning falls back to standard Alimama inpainting
d) New group for preprocessing the image for Depth or Canny
e) Canny or Depth reference image for Outpainting
• Depth: fast-fill in a more complex way
• Canny: pads outpainting with black
f) Canny or Depth works with localized area option
🔹🔹 New: Aura Mask implemented back on the COMPACT workflow with convenient easy to use toggle and sliders.
🔹🔹🔹 A bunch of smaller Changes:
1. Fixed old to new “✂️ Inpaint Crop (Improved)”
2. LoAd Loras: now using "Lora Stacker (LoraManager)" node
→ It’s better and everyone should use LoraManager — fantastic custom node
3. Fixed: “GrowMask” 5 px not connected on the outpainting fast-fill for better blending
4. Added a slider for “Image Resize Resolution”
5. Nodes cleanup:
→ Replaced some “crystools” switch nodes with “easy-use” switches
→ Reducing dependency on custom nodes (some “crystools” may remain)
→ Same gradual cleanup plan for “Logic” nodes
→ Updated control-room logic nodes to “easy-use”
6. “Logic operator” > “easy-use” for negative thresholding
→ Uses index instead of bool
7. “Logic operator” > “easy-use” for localized area inpainting
→ Uses index instead of bool
8. “✂️ Inpaint Stitch (Improved)” moved outside localized area inpainting group (not on COMPACT)
→ It is now auto-muted by a muter
9. “Get LoRAs names and process it do Get metadata” group updated:
→ Evaluates if LoRAs are in use in a different way
→ Adds clean LoRA names to the positive prompt with 🖌️ and 🎯 for full LoRA syntax
10. Fixed saving negative prompt on metadata: will first save the retrieved original negative prompt and if that is OFF, it will only save inpainting negative IF using thresholding.
11. It will always evaluate if Positive is empty (if retrieving the original positive prompt fails) and if it is, it uses the inpainting prompt to save in the metadata.
12. Fixed: for Compact: "SD Prompt Reader" won't error when retrieving loaded image original metadata that used SAM Detector to make a mask.