haoailab· @haoailab · X·· 3 小时前AI 评分
FastVideo 支持图像+语音多模态推理
6/7 Serve it: one image + one voice on 4x— GB200, then 8 GPUs across two hosts for bigger reference mixes. Pinned checkpoints and configs. Star the repo, try it in ComfyUI, and tell us what you make. Blog: haoailab.com/blogs/fastvideo… Model: huggingface.co/collections/F… Uniserve: github.com/hao-ai-lab/uniser… FastVideo Repo: github.com/hao-ai-lab/FastVi…
6/7 推理部署:在 4 台 GB200 上实现单图单语音推理,对于更大的参考混合则使用跨两台主机的 8 张 GPU。已固定检查点和配置。
给仓库点个 Star,在 ComfyUI 中试用,然后告诉我们你的创作成果。
博客:haoailab.com/blogs/fastvideo…
模型:huggingface.co/collections/F…
Uniserve:github.com/hao-ai-lab/uniser…
FastVideo 仓库:github.com/hao-ai-lab/FastVi…
来源:haoailab · x.com