Open nono-Sang opened 4 months ago
对 issue https://github.com/siliconflow/onediff/issues/857 以及 https://github.com/siliconflow/onediff/issues/778 的修复。
修改后,output_shape = hs[-1] 是让 Upsample 进入到:https://github.com/siliconflow/onediff/blob/4852e8a3aa254ae248e12ce4863d0a332f858a15/onediff_comfy_nodes/modules/oneflow/infer_compiler_registry/register_comfy/openaimodel.py#L20 即最终调用 interpolate_like 而非另一个条件下的 interpolate。
output_shape = hs[-1]
Upsample
interpolate_like
interpolate
这样,DeepCacheUNet / FastDeepCacheUNet 也与 UNetModel 保持一致了:https://github.com/siliconflow/onediff/blob/4852e8a3aa254ae248e12ce4863d0a332f858a15/onediff_comfy_nodes/modules/oneflow/infer_compiler_registry/register_comfy/openaimodel.py#L145
DeepCacheUNet / FastDeepCacheUNet
UNetModel
对 issue https://github.com/siliconflow/onediff/issues/857 以及 https://github.com/siliconflow/onediff/issues/778 的修复。
说明
修改后,
output_shape = hs[-1]
是让Upsample
进入到:https://github.com/siliconflow/onediff/blob/4852e8a3aa254ae248e12ce4863d0a332f858a15/onediff_comfy_nodes/modules/oneflow/infer_compiler_registry/register_comfy/openaimodel.py#L20 即最终调用interpolate_like
而非另一个条件下的interpolate
。这样,
DeepCacheUNet / FastDeepCacheUNet
也与UNetModel
保持一致了:https://github.com/siliconflow/onediff/blob/4852e8a3aa254ae248e12ce4863d0a332f858a15/onediff_comfy_nodes/modules/oneflow/infer_compiler_registry/register_comfy/openaimodel.py#L145