MOSS

Connecting AI, humans, and the physical world.
TTS｜ASR｜VL ｜Audio｜Video｜Contextual Intelligence
⚡️Vibe with us:

[MOSS @MOSS_Global]

MOSS-Image API is coming soon in 24hrs

Join MOSS discord for FREE early access 👉 https://t.co/pvnlNegist

[MOSS @MOSS_Global]

https://t.co/1wLxz2idJz

[MOSS @MOSS_Global]

MOSS-Image-SFT in just 4 steps. ⚡

@_akhaliq 's community distillation has reached 16.5K+ downloads on Hugging Face.
Thanks for building and sharing! Try it on your own prompts ↓

[MOSS @MOSS_Global]

@hellorob Thanks for putting this together, Rob! Great to see the color-depth adapter in action. Huge thanks to everyone in the ComfyUI community building with MOSS Image 🙌

[rob - comfyui @hellorob]

MOSS Image dropped less than a week ago and it’s already at 1.29M downloads on Hugging Face.

If you have consumer hardware, this open source image model is for you + FREE workflow below
→ 5B params
→ int8 weights are only 5.4GB
→ Apache 2.0 license
→ seamless install via Comfy Desktop
The quality punches way above it's weight. Great work by @Open_MOSS.

What the ComfyUI community shipped in 5 days:
→ color + depth control adapter (darask0)
→ hires LoRA, native 4096×2304 gens (thee comfyanonymous)
→ LoRA training support all the major tools
→ Kromoss finetune, with a 8step DMD2 turbo LoRA (lodestones)
→ DSLR realism LoRA (Danrisi)

I built a workflow for the color-depth control adapter running in ComfyUI. Prompt adherence and detail is spot on (check the lens flare).

[Ting Chen Liang @ting_]

MOSS image FAST AS HELL TURBO by @_akhaliq

50 steps → 4 steps ⚡

turbo feels like a sweet spot for generating lots of images fast

regular text posters still look pretty good too. tiny lettering gets a bit blurry, so i'd stick with the original SFT for text-heavy designs!

Base 50 steps 🆚 SFT 50 steps 🆚 4-step version side by side comparison👇

[Sogni.ai @Sogni_Protocol]

MOSS-Image SFT and MOSS-Image 8-Step are now on Sogni, and both are included in Sogni Unlimited

It’s OpenMOSS’s 5-billion-parameter text-to-image model, made for text. Quote the words in your prompt and it writes them out exactly, from long instructions and terminal commands to full menus, in English and Chinese.

Every image in this thread was made with it 👇🧵

[Civitai @HelloCivitai]

MOSS Image is live on Civitai.

A 5B open-weights text-to-image model from the OpenMOSS team. Text that reads right, JSON layout control, and prompts up to 4K tokens. Apache 2.0.

You can also train LoRAs on it in the Training Studio.

Try it: https://t.co/hoVY4Xk89D

[MOSS @MOSS_Global]

@bdvd_25 what do you say @ComfyUI

[MOSS @MOSS_Global]

Try MOSS-Image in ComfyUI with our free API. 🎨

⚡ Get your API key: https://t.co/kywj8NhxTp

[MOSS @MOSS_Global]

Manga panels with vertical Japanese text and sound effects, using layout control and a character LoRA.
https://t.co/T8zaNBWrod

[Kamimoto(かみもと) @sep_is_heim]

MOSS Imageで漫画作成トライ！少しガチャいるけど日本語の縦書きもいけるし、効果音もいける。何よりコマ割りレイアウトが漫画っぽい！bboxで指定したけど、ここまで出来ると評価が変わるなー。キャラLoRAあり。プロンプトはリプへ。

[MOSS @MOSS_Global]

Love seeing what you're building with MOSS-Image. Thanks for sharing your work.
If you'd like to experiment too, our MOSS-Image API is free to try: https://t.co/9ywAcuQH1u

Here are a few community projects and experiments that caught our eye 👇

[MOSS @MOSS_Global]

16��16-style game icons with a pixel-art LoRA.
https://t.co/uS8BjWBRkv

[Angel 🌼 @Angaisb_]

Published a LoRA for MOSS too

You can download it here: https://t.co/RP9cWJpSaZ