Michael
Michael
Hi guys! Is it possible that in the future we will see LORA functionality from the diffusion models? **For example:** 1. Connecting multiple LORAs at the same time 2. LORA...
Hi, can you suggest how to merge the base model and the trained vector?
It seems adapting the code for some web interfaces causes problems with generating all-black clothing, or with some elements (spots) of the reference clothing on generation. Is it possible that...
你好,我想使用 Light2xv 推理来运行 Wan 2.2 微调模型(目前仅有 FP8 non-scaled 版本),但我发现需要 _scaled 版本。请问是否可以使用标准的 FP8 版本代替? 将模型转回 bf16 以创建 scaled 版本对我来说似乎不是一个合理的解决方案,但如果不修改仓库代码,我似乎别无选择。请问这种情况下有什么可用的方案?