Akhaliq's MOSS-Image-SFT 4 step Lora v.2.0 - 4 step v2.0

Akhaliq's MOSS-Image-SFT 4 step Lora v.2.0

LORA
Reprint


Updated:

Akhaliq's MOSS-Image-SFT 4 step Lora v.2.0 by gpxumuk on Tensor.Art
Akhaliq's MOSS-Image-SFT 4 step Lora v.2.0 by gpxumuk on Tensor.Art
Akhaliq's MOSS-Image-SFT 4 step Lora v.2.0 by gpxumuk on Tensor.Art
Akhaliq's MOSS-Image-SFT 4 step Lora v.2.0 by gpxumuk on Tensor.Art

A 4-step lora for MOSS image by akhaliq .

Sampler/Scheduler: Euler, sgm_uniform, simple or MOSS (original scheduler from MOSS Image creators; included inside the Moss Image Forge Neo plugin by eduardoabreu81)

Steps: > 4 . I use 8-10, sometimes even this is not enough.

CFG: 1-3 depending from prompt and resolution.

Original creator's notes:

🆕 v2.0 (2026-10-18) — major update, usage changed. The model is now Euler-native: a single lora.safetensors that runs on the stock flow-matching Euler sampler (any LoRA loader, 4 steps, CFG 1) — the custom data-space sampler and the time_embedding.safetensors / dataspace.safetensors files are no longer needed and were removed from the repo root. If you used v1.x adapters, grab the old data-space variant from checkpoint-update-400/ (it keeps its own sampler), or switch to the new one-line loader below. New users: just follow the Quickstart.

License: Apache-2.0 — commercial use OK.

Version Detail

MOSS-Image-SFT

Project Permissions

Model reprinted from : https://huggingface.co/akhaliq/MOSS-Image-SFT-4-steps

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Related Posts