When I tried to generate an image conditional on semantic maps, there was an issue with the output shape. According to the definition of the following source code, controlling the output shape by setting height and width is achievable. However, it doesn't work out, for example, input height = 520, width = 480, and the output image could be in other shapes.
Hi, thank you for the great work!
When I tried to generate an image conditional on semantic maps, there was an issue with the output shape. According to the definition of the following source code, controlling the output shape by setting height and width is achievable. However, it doesn't work out, for example, input height = 520, width = 480, and the output image could be in other shapes.
https://github.com/huggingface/diffusers/blob/c586aadef6bb66d355fa40a2b95a0bea8a6fe79c/src/diffusers/pipelines/controlnet/pipeline_controlnet.py#L908