MOSS-Image-Base style fine-tune (amateur photo)

Full fine-tune of the MOSS-Image-Base DiT (text encoder and VAE frozen) with DiffSynth-Studio, 1 epoch over 11,264 caption rows, lr 1e-5, 1 MP aspect-bucketed.

checkpoints/step-N.safetensors: bf16 DiT, same keys as the base transformer/ (loads in ComfyUI as is)
int8_convrot/step-N_int8_convrot.safetensors: INT8 ConvRot, same layout as Comfy-Org/MOSS-Image moss_image_base_int8_convrot

Use with the Comfy-Org MOSS-Image Base workflow (Qwen3.5 text encoder, FLUX.2 VAE).

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for lamshiu/moss-image-style-ft

Base model

OpenMOSS-Team/MOSS-Image-Base

Finetuned

(27)

this model