How to train a MOSS Image LoRA

Which trainers support MOSS Image (OpenMOSS, ~5B, Apache 2.0), how much VRAM you need, and settings that are known to work. Every row links to its source.

Trainer support

Trainer	Status
ai-toolkit	supported (SFT + Base, Oct 16)
OneTrainer	unknown
musubi-tuner	unknown
kohya sd-scripts	unknown
SimpleTuner	unknown

VRAM

~15 GB at batch 2, 1024px, AdamW, 15 images, ~2 s/step on RTX Pro 6000 (single community report) [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]

Known-good settings

Learns fast [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]
Tokenizer loading bug fixed same day (Oct 16) in ai-toolkit; update before training
SFT variant: stripe artifacts reported, unresolved [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]

General tips

Gated Hugging Face models: click 'Agree and access' on each model page, or you'll get 403 errors
Steps scale with dataset size (steps = epochs x images at batch 1)
Common safe start: LoKr with auto rank (~64), batch/grad accumulation 4 [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]

Where to rent a GPU

See cheapest GPU to train a LoRA (RunPod, Vast.ai).

Sources

Weekly newsletter: new models, trainer releases, cheapest GPUs. Subscribe

Data updated 2026-10-16. Some provider links may be referral links. unknown = not yet verified.