# AI OSS Daily · Picks archive · 2026-06-03

Auto-updated daily around 09:00 and pushed straight to your Telegram — free, no ads, unsubscribe anytime.

- [SulphurAI/Sulphur-2-base](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-sulphurai-sulphur-2-base/) — text-to-video · diffusers, safetensors, gguf
- [OpenMOSS-Team/MOSS-TTS-v1.5](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-openmoss-team-moss-tts-v1-5/) — text-to-speech · safetensors, moss_tts_delay, text-to-speech
- [stabilityai/stable-audio-3-medium](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-stabilityai-stable-audio-3-medium/) — text-to-audio · stable-audio-3, safetensors, audio-generation
- [Supertone/supertonic-3](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-supertone-supertonic-3/) — text-to-speech · supertonic, onnx, text-to-speech
- [nvidia/Cosmos3-Super-Text2Image](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-nvidia-cosmos3-super-text2image/) — text-to-image · cosmos, diffusers, safetensors
- [LiquidAI/LFM2.5-8B-A1B](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-liquidai-lfm2-5-8b-a1b/) — text-generation · transformers, safetensors, lfm2_moe
- [nvidia/Cosmos3-Super-Image2Video](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-nvidia-cosmos3-super-image2video/) — image-to-video · cosmos, diffusers, safetensors
- [microsoft/Lens](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-microsoft-lens/) — text-to-image · diffusers, safetensors, text-to-image
- [nvidia/PiD](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-nvidia-pid/) — image-to-image · pytorch, diffusers, safetensors
- [openbmb/MiniCPM5-1B](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-openbmb-minicpm5-1b/) — text-generation · transformers, safetensors, llama
- [nvidia/Qwen3.6-35B-A3B-NVFP4](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-nvidia-qwen3-6-35b-a3b-nvfp4/) — text-generation · Model Optimizer, safetensors, qwen3_5_moe
- [prism-ml/bonsai-image-ternary-4B-gemlite-2bit](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-prism-ml-bonsai-image-ternary-4b-gemlite-2bit/) — text-to-image · diffusers, safetensors, ternary