City
City
*I figured this is the easiest place to open this issue, but I can probably reproduce it on the [reference implementation](https://github.com/Stability-AI/generative-models) (or diffusers) and post my issue there, if required.*...
Currently, the `load_image` function in `train_utils` uses the PIL `image.convert("RGB")` method for converting the loaded 4 RGBA channel images to the expected 3 channel RGB format. This is incorrect for...
I've been alerted that the following merged PR https://github.com/Tencent/HunyuanDiT/pull/59 seems to take large large parts of code from the following [ComfyUI custom node](https://github.com/city96/ComfyUI_ExtraModels) with **no attribution** to me or chaojie...
At this point, there is no way to not address your recent behavior at least in some form. In the [following PR](https://github.com/lllyasviel/stable-diffusion-webui-forge/pull/1482), you wrote the following: >Although I still find...
The plan is to do a full rewrite/refactor of this repo to have better integration with most of the native comfy code. This should make things less fragile (and less...