license: other
language:
- en
base_model:
- black-forest-labs/FLUX.1-dev
library_name: diffusers
pipeline_tag: text-to-image
emoji: 🌊
tags:
- FluxPipeline
- FLUXv1-dev
- image-generation
- flux-diffusers
- diffusers
- art
- realism
- photography
- illustration
- merge
- base
- anime
- full finetune
- trained
- finetune
- trainable
- full-finetune
- checkpoint
- text2image
- Schnell
- Flux
- Dev
- De-distilled
- dedistilled
- PixelWave
- Booru
- FluxBooru
widget:
- text: '-'
output:
url: MangledMergeV1.jpeg
- text: '-'
output:
url: MangledMergeV1iii.jpeg
- text: '- '
output:
url: MangledMergeV1ii.jpeg
- text: '- '
output:
url: MangledMergeV1iv.jpeg
- text: '-'
output:
url: MangledMergeV1vi.jpeg
MANGLED MERGE V1.0
Herein lives a HF/Diffusers-ported version of the Mangled Merge Flux - v1.0 model by pmango300574.
Quoth pmango300574's write-up for their model:
Mangled Merge V1 is a merge of Mangled Merge Flux Matrix, Mangled Merge Flux Magic, PixelWave 03 (or HF/Diffusers port here), FluxBooru v0.3, and Flux-dev-de-distill, to create a model that offers the aesthetics of 808 merged LoRAs, with the styles of PixelWave, the knowledge of the Booru dataset and the functionality of a dedistilled model!
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
LoRAs work fine with this model,
CFG is best between 1 and 3.5,
Flux Guidance doesn't work, but negative prompts work great, and I HIGHLY recommend using dynamic thresholding.
For a model comparison between Mangled Merge V1 vs. Flux.1 Dev, check out this post.