| MOSS-Audio-8B-Instruct-ComfyUI | |
| Original model authors/publisher: lakucho/MOSS-Audio-8B-Instruct. | |
| Source: https://huggingface.co/lakucho/MOSS-Audio-8B-Instruct/tree/8bd5b22c64dd80b59c06af4e3304e581a3e5596b | |
| Repackaged by Jack Spooner for native ComfyUI on 19 October 2026. | |
| MODIFIED FILES: All distributed model .safetensors files are converted/split derivatives, with native key/layout and embedded-asset changes described in README and PROVENANCE.json. The underlying model authors retain their rights. | |
| Repackages the exact lakucho mirror revision, preserving 901 BF16 source tensors and embedding its tokenizer. This is an OpenMOSS model distributed via that mirror; it is not our fine-tune. | |
| The pinned mirror model card declares Apache-2.0 and credits OpenMOSS. Both the actual source mirror and the original OpenMOSS authors are attributed. | |
| ComfyUI integration code is distributed separately at https://github.com/jackspooner/ComfyUI; its own license and retained third-party notices apply to that code. | |
| Original authors: OpenMOSS Team, MOSI.AI and Shanghai Innovation Institute. Qwen3 backbone credits remain with Qwen/Alibaba Cloud. | |