Layerdiffuse

[githabtane]

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits

What would your feature do ?

The extension "LayerDiffuse" works on the "main" branch, but an error occurs on the "dev_upstream" branch. Is there any solution? I don't understand English, so I'm sorry that I can't explain it well.

Proposed workflow

1

Additional information

1

[Panchovix]

I have fixed it on last commit, thanks for the report.

https://github.com/Panchovix/stable-diffusion-webui-reForge/commit/eea0d9b9d791bdbbef8a7bd0d82d4b1e349ecb7b

[githabtane]

Traceback (most recent call last): File "D:\Forge\stable-diffusion-webui-reForge\modules\call_queue.py", line 74, in f res = list(func(*args, **kwargs)) TypeError: 'NoneType' object is not iterable

[Panchovix]

Now it should be fixed after https://github.com/Panchovix/stable-diffusion-webui-reForge/commit/f607c9a24219978ed6499ff125eb9eb9d4adf1f6

VAE clone was missing come values

[githabtane]

---

[Layer Diffusion] LayerMethod.FG_ONLY_ATTN_SD15 Error running process_before_every_sampling: D:\ReForge2\stable-diffusion-webui-reForge\extensions\sd-forge-layerdiffuse\scripts\forge_layerdiffusion.py Traceback (most recent call last): File "D:\ReForge2\stable-diffusion-webui-reForge\modules\scripts.py", line 885, in process_before_every_sampling script.process_before_every_sampling(p, script_args, kwargs) File "D:\ReForge2\stable-diffusion-webui-reForge\extensions\sd-forge-layerdiffuse\scripts\forge_layerdiffusion.py", line 226, in process_before_every_sampling patcher = AttentionSharingPatcher(unet, frames=1, use_control=False) File "D:\ReForge2\stable-diffusion-webui-reForge\extensions\sd-forge-layerdiffuse\lib_layerdiffusion\attention_sharing.py", line 208, in init attn_module = utils.get_attr(unet.model.diffusion_model, real_key) File "D:\ReForge2\stable-diffusion-webui-reForge\ldm_patched\modules\utils.py", line 397, in get_attr obj = getattr(obj, name) File "D:\ReForge2\stable-diffusion-webui-reForge\venv\lib\site-packages\torch\nn\modules\module.py", line 1695, in getattr raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'") AttributeError: 'TimestepEmbedSequential' object has no attribute '1'

[githabtane]

[githabtane]

main branch

[githabtane]

python 3.10.11 NVIDIA GeForce RTX 4060 Ti 16GB controlnet softedge error pip install basicsr<< works fine Is there a problem with "requirements.txt"? I'm an amateur so I don't really understand.

[Panchovix]

So did you install basicsr and it worked fine?

Maybe requirements.txt could have that but it should a req of layer diffusion when installing it