wowsuch ai
Live

sselpahModel

Moss:RAEL

Moss:RAEL is an anime-focused fine-tune of MOSS-Image-Base. It is intended to reconstruct anime imagery and expressive linework.

What it does

Use it to generate anime-style images from prompts specifying artists, anime screencaps, or copyright subjects.

Availability
Model and workflow are available on Hugging Face
Pricing model
Not established
Deployment
Not established
Privacy
Not established
Licence
Not established
Capability
image generation
Modality
image
Access
open weights
Deployment
on-premises
Pricing
unknown
Target user
creator

Evidence

4 claims
  • Moss:RAEL is an anime-focused fine-tune of MOSS-Image-Base.
  • The model is trained on approximately 68,000 Danbooru illustrations and anime screenshots. [1]
    - **Dataset:** Custom closed dataset of 68,000~ danbooru illustrations/anime screenshots (85%/15%)
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model works nicely at 1 MP–1.5 MP. [1]
  • A workflow JSON file is provided on the Hugging Face model page.

Sources

1
1
Hugging FaceOwner-controlled
https://huggingface.co/sselpah/MossRAEL Retrieved 2026-11-03 01:12 UTC
Verified

Versions

1
VersionEffectiveChangeChanged fieldsState
12026-11-03 01:13 UTCpublicationNoneCurrent

Open in the catalog

Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.