Model reference · open weights
moeFussion is an open-weight image model from LoliRimuru. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | LoliRimuru |
|---|---|
| Type | Image models |
| Task | Text→image |
| Runs with | diffusers |
| Released | 2023-02-28 |
| Popularity | 41k downloads / month |
| Licence | Open weights |
About
The goal of this project is to improve generation of moe characters since most of other models are not good at it.
Some of the models can be used online on these plarforms:
Aipictors (Japanese) - https://www.aipictors.com
It is recommende to use standard resolution such as 832x1144
Positive prompt example: masterpiece, best quality, 1girl, solo, full body, night, purple kimono, japanese clothes, barefoot, obi, bare legs, braided ponytail, feet, mole, toes, collarbone, toenails, electricity, looking at viewer, night sky, holding weapon, holding, holding polearm, floating, sakura, petals
Negative prompt example: lowres, worst quality, low quality, old, early, bad anatomy, bad hands, 4koma, comic, greyscale, censored, jpeg artifacts, monochrome, simple background,
All examples were generated using custom workflow in ComfyUI and weren't edited using inpainting. You can load the workflow by either importing the example images or importing the workflow directly
Discord: https://discord.gg/mZ3eGeNX7S
v3.0
Anima v1 based
Better anatomy, smaller model, better prompt adherance
Use @artist for artists, case sensitive
You can use both tags and natural language prompts and you will likely achieve better results combining both
It's better to use longer prompts for better results, shorter (sub 10 tags) may result in lower quality
Use er_sde sampler and simple or maybe beta scheduler, cfg around 4 maybe even closer to 3
v0.4.3
Fixed color issue
General improvements
v0.5.3
Integrated VAE
File size reduced
CLIP force reset fix
v0.6.3
Style improvements
Added PastelMix and Counterfeit style
v0.7.x
Style impovements
Composition improvements
v0.8.x
Major improvement on higher resolutions
Style improvements
Flexibility and responsivity
Added support for Night Sky YOZORA model
v0.9.x
Different approach at merging, you might find v0.8.x versions better
Changes at supported models
v2.1.X EXPERIMENTAL RELEASE
Stable Diffusion 2.1-768 based
Default negative prompt: (low quality, worst quality:1.4), (bad anatomy), extra finger, fewer digits, jpeg artifacts
For positive prompt it's good to include tags: anime, (masterpiece, best quality) alternatively you may achieve positive response with: (exceptional, best aesthetic, new, newest, best quality, masterpiece, extremely detailed, anime, waifu:1.2)
Though it's Loli Diffusion model it's quite general purpose
The ability to generate realistic images as Waifu Diffusion can was intentionally decreased
This model performs better at higher resolutions like 768*X or 896*X
v0.10.x
Different approach at merging
Better hands
Better style inheritance
Some changes in supported models
v0.11.x
Slight changes
Some changes in supported models
v0.13.x
Slight model stability improvements
Prompting loli requires lower weight now
v0.14.x
Many model support changes
Using merging concept from v0.10 but improved as 13 and 11 had unwanted side effects
Composition and anatomy should be more coherent now
Improved multi-character generation
v1.1.x XL
Uses Pony XL as a base
Transfers benefits of XL and tries to improve on backgrounds of Pony
v1.2
this is SDXL V-Pred + ZTSNR series models
Cfg: around 5
Sampler: normal Euler is suggested
Sheduler: normal or AYS
Steps: 30
you will need SwarmUI or ComfyUI to run them, while they should get autodetected it's suggested to manually specify the model as zsnr+vpred
v1.3
Illustrious v1 based
Resolution raised to 1536x1536
There are 2 versions II - more raw, more control, suitable for LoRA and IIZ - default style, easier to use, more bias to loli chara
It's better to use longer prompts for better results, shorter (sub 10 tags) may result in lower quality
Improved composition and prompt adherence (both natural to a degree and booru)
https://huggingface.co/datasets/gsdf/EasyNegative
https://huggingface.co/WarriorMama777/OrangeMixs
https://huggingface.co/hakurei/waifu-diffusion-v1-4
https://huggingface.co/gsdf/Counterfeit-V2.5
https://civitai.com/models/12262?modelVersionId=14459
https://civitai.com/models/149664/based67
https://huggingface.co/gsdf/Counterfeit-V2.5
https://huggingface.co/Yntec/EstheticRetroAnime
https://huggingface.co/dwarfbum/Hassaku
https://huggingface.co/stb/animelike2d
https://huggingface.co/circlestone-labs/Anima
From the published model card. Full card on the HuggingFace links in the sidebar.
How it works
Using it via the API
Once AxForge deploys moefussion for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (moefussion below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/images/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"moefussion","prompt":"a red bicycle","size":"1024x1024"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.