Sign In
home
models
images
videos
posts
articles
bounties
tools
challenges
events
shop

♾️ Merge Recipe for mugenMaluMix v4.1

13
motimalu's Avatar
motimalu
Supporter Badge March 2024
May 9, 2024
resource guide
merge recipemergescomfy_uidaresupermerger

MugenMaluMix v4.1

Sharing the merge recipe for the Pony Diffusion merge checkpoint MugenMaluMix mix version 4.

This version is inspired by the DARE merging described by the paper Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

The intended use of this merge checkpoint is to produce Game Art, Anime, and Character subjects in a Fantasy style.

New in this version:

  • Used DARE merging through ComfyUI with gradient masking to create the base model

  • Merged updated and additional new finetune checkpoints:

  • Applied new styles and concepts though the inclusion of new LoRAs

  • Continued use of a hierachical merge approach to asses the priority & weights of each LoRA category (Styles, Concepts, Characters)

  • Improved responsiveness to and compatibility with "masterpeice, best quality, very aesthetic, absurdres" quality tagging

  • Reduced the oily/shiny appearance of skin

  • Better high dynamic range, color saturation and contrast of base outputs

Quality goals remain to prioritise better anatomy (hands, feet particularly) and maintain the base models responsiveness to booru tagging.

📔Resource Overview

🚩Checkpoints

🖌LoRAs by author motimalu

Grouped by homogulous traits for DARE LoRA merging

Game Art:

Artists:

Monmusu:

Fluffy Tail

Frieren:

Mushoku:

🖌Community LoRAs

"RGB Gemstone" group, these give great improvement to color saturation, contrast, and fine details on jewelery, eyes reflections and lighting:

🧙‍♂️Merge setings

Merge tool: ComfyUI

Merge Nodes from:

Merge Strategy:

1: Hierachical DARE Checkpoint merge with gradient masking

2: DARE Merge of LoRA stacks sorted into similar categoties are created

3: Weights for each LoRA are determined though testing before baking into the final model

Step 1. Sequential DARE merge of base models

ℹ️ComfyUI workflows are embedded in the images.

AutismMix SDXL merged with 4th tail (Hentai model) v.0.4.0

Merged with Omega Pony XL anime style

Merged with T-ponynai3 v.4.1

Step 2. DARE merge of LoRA groups

ℹ️ComfyUI workflows are embedded in the images.

Game Art:

Artists:

Monmusu:

Fluffy Tail:

RGB Gemstones:

Frieren:

Mushoku:

Saved the result up to here as merge model: mugenmalumixSDXL_v41_base

Step 3. LoRA merge to checkpoint

X/Y Comparisons of the DARE LoRA's effect to determine a final weights to bake into the checkpoint:

With a bit more testing of how these work in tandem, I decided on these weights:

  • rgb_gemstones: 0.42

  • mushoku: 0.40

  • gameart: 0.25

  • monmusu: 0.25

  • fluffytail: 0.25

  • frieren: 0.20

  • artists: 0.15

With the desired weights determined, the LoRA patch to the checkpoint is saved as the LoRA finetune model: mugenmalumixSDXL_v41_delorean

🧪Results:

X/Y checkpoint comparison plots of some results for prompts that emphasize characteristics of this merge:

That's it!

Please feel free to share your thoughts/feedback on this version in the comments below. ´ ˘ `

13

Comments