@MOSS_Global

Connecting AI, humans, and the physical world. TTS｜ASR｜VL ｜Audio｜Video｜Contextual Intelligence ⚡️Vibe with us: https://xitter.cf/t.co/Lmk4Kd65JJ

platform.mosi.cn/?utm_source=twitter&utm_medium=social&utm_campaign=profile&utm_content=mosi
Joined January 2026
  • Tweets348
  • Following28
  • Followers2.1K
73Media
MOSS-Image API is coming soon in 24hrs Join MOSS discord for FREE early access 👉 discord.gg/Wjku5AYyxx
5
4
2
77
2,626
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: platform.mosi.cn/?utm_source… Here are a few community projects and experiments that caught our eye 👇
3
3
44
1,668
more replies
16×16-style game icons with a pixel-art LoRA. xitter.cf/Angaisb_/status/211121…
Angel 🌼
@Angaisb_Oct 16
Published a LoRA for MOSS too You can download it here: huggingface.co/Angais/MOSS-I…
1
3
162
Manga panels with vertical Japanese text and sound effects, using layout control and a character LoRA. xitter.cf/sep_is_heim/status/211…
Kamimoto(かみもと)@sep_is_heimOct 18
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。
4
152
I think @MOSS_Global is my favorite new local image model. It is fantastic at prompt adherence and I love the quality and its versatility. Here are some more examples I just generated.
2
2
13
363
If your training MOSS-Image LoRAs, i got a pro tip ive found helps: LOW LR is the best way to go. (and i mean like 0.00003) avoids burning the outputs. i may retrain my RebelReal LoRA i wont lie. my Midjourney LoRA outputs are looking insane right now.
9
2
74
3,157
It was the pigeon Moss-image (prompt below)
3
1
16
603
MOSS-Imagine (bf16) workflows in the repo as well! includes the Qwen prompt enhancer huggingface.co/realrebelai/M…
2
1
32
1,408
MOSS retweeted
toyxyz
@toyxyz3Oct 19
huggingface.co/darask0/MOSS-…

darask0/MOSS-Image-color-depth-control · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co
6
41
3,038
Moss Img 🥰 NiceGirls v2 Realism Lora 👇 huggingface.co/Danrisi/niceg…
3
95
6,806
ComfyUI MOSS Prompt Enhancer Turn basic ideas into killer descriptive prompts & exact spatial layouts, running locally with GGUF. github.com/slmonker/ComfyUI-…

GitHub - slmonker/ComfyUI-MOSS-PromptEnhancer: Local GGUF prompt generation for MOSS-Image in...

Local GGUF prompt generation for MOSS-Image in ComfyUI, with Caption/Layout modes and Chinese text preservation. - slmonker/ComfyUI-MOSS-PromptEnhancer

github.com
5
16
1
191
11,016
MOSS Imageベースの部分再描画ワークフロー「MOSS Image inpainting workflow」が公開 塗ったマスク範囲のみを短いプロンプトで描き直すComfyUI構成 マスク外をピクセル単位で維持する部分編集を実現 #MOSSImage #ComfyUI URLはリプ⬇️
3
14
2
117
5,417
MOSS-Image can actually spell. I put it against Qwen Image 2.1 and FLUX 3 Klein, then went through my ComfyUI workflow for it, switch by switch. youtu.be/CF8pIIlV9-0 @MOSS_Global
1
1
6
260
Load more