๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

MOSS
@MOSS_Global
Connecting AI, humans, and the physical world. TTS๏ฝœASR๏ฝœVL ๏ฝœAudio๏ฝœVideo๏ฝœContextual Intelligence โšก๏ธVibe with us:
๊ฐ€์ž… January 2026
34 ํŒ”๋กœ์ž‰ ์ค‘    3.3K ํŒฌ
๐Ÿค— MOSS-Image is now open source on @huggingface . Built on a 5B Diffusion Transformer (DiT), MOSS-Image brings Chinese & English text rendering and controllable layouts to image generation โ€” from posters and infographics to creative visuals.@Open_MOSS What it offers: ๐Ÿ“ Long prompts & text rendering โ€” up to 4K-token prompts, including multi-line text ๐Ÿ“ Experimental JSON layout control โ€” specify text, objects, and their positions using bounding boxes ๐Ÿ–ผ๏ธ Flexible generation โ€” multiple aspect ratios, resolutions, and customizable inference settings ๐Ÿ› ๏ธ Developer workflows โ€” Python (Diffusers), Gradio, ComfyUI, and a Prompt Enhancer Skill ๐Ÿ“ฆ Base & SFT checkpoints are both available, with open model weights and Apache-2.0 licensed inference code. ๐Ÿ™Œ Huge thanks to @sgl_project @vllm_project @ModelScope2022 for the Day-0 support!
๋” ๋ณด๊ธฐ