Álvaro Somoza
Álvaro Somoza
# What does this PR do? Initial draft to support for official callbacks. This is the most basic implementation I could think of without the need of modifying the pipelines....
# What does this PR do? When using some LoRAs, for example [sd_xl_offset_example-lora_1.0.safetensors](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_offset_example-lora_1.0.safetensors) with blockwise scales we get this error: ``` RuntimeError: No LoRA weight found for module down_blocks.0.resnets.0.conv1 ```...
### Describe the bug When loading the [sd_xl_offset_example-lora_1.0.safetensors](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_offset_example-lora_1.0.safetensors) from the [official repository](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/) and setting the scales by blocks, it throws this error: `RuntimeError: No LoRA weight found for module down_blocks.0.resnets.0.conv1`...
# What does this PR do? Tests for the official callbacks introduced in #7761 - [X] official callback test - [ ] multiple official callbacks test - [X] SD tests...
# What does this PR do? Fix a recurring problem when using diffusers without console, e.g. using `pythonw.exe` in windows, since there's no `sys.stderr`. I can make a more advanced...