OpenMoss team releases MOSS Image Base and SFT text-to-image models
Moss Image Base & SFT- Light model for Text to image generation
AI briefing
The OpenMoss team released two versions of MOSS Image, Base and SFT. The generative model is a 5B-parameter single-stream Diffusion Transformer (DiT), pretrained from scratch, aimed at dense bilingual text and multi-element graphic generation.
Open original stablediffusiontutorials.com
Image GenerationComfyUI & WorkflowsTutorials & Practice#Tutorial#Image generation#ComfyUI & workflows