Since CivitAI is going down THE DRAIN

v7.0 Compact Video: https://youtu.be/oY1B-5x9kh4

🔹 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.