Repository: localaiLicense: apache-2.0

MOSS-Image-SFT is the supervised fine-tuned variant of MOSS-Image, a 5B diffusion transformer image generation model from OpenMOSS-Team. It uses Qwen3.5 9B as the LLM text encoder, the FLUX.2 VAE, and an external tokenizer. The SFT variant produces higher-quality outputs with classifier-free guidance (default: CFG 3.0, 1024x1024). This entry uses the int8_convrot quantization of the diffusion model (~5.4 GB).
Links
Tags
Repository: localaiLicense: apache-2.0
MOSS-Image is a 5B diffusion transformer text-to-image model that uses the FLUX.2 VAE and a Qwen3.5 9B text encoder. This is the SFT variant. This is the Q4_K quantization of the diffusion model (~3.3 GB) by leejet for stable-diffusion.cpp. The bundle also pulls the Qwen3.5 9B Q4_K_M text encoder (~5.7 GB), the FLUX.2 VAE and the Qwen3.5 tokenizer file, which must be given explicitly because Qwen3.5 does not use the embedded Qwen vocabulary. Use image dimensions divisible by 16.
Links
Tags