[Feature] sd-forge-layerdiffuse

[brunogcar]

Issue Description

i guess this would be more of a feature request than extension or sdnext issue as that extension was made based on modifications of sd-force - Layer Diffusion for WebUI (via Forge)

so, as expected it wouldnt work on sdnext and it is kinda pointless to open issue there to ask for sdnext support

but still, a neat feature that would be quite usefull to have here

22:27:44-335936 ERROR    Module load: extensions\sd-forge-layerdiffuse\scripts\forge_layerdiffusion.py:
                         ModuleNotFoundError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ E:\GitHub\TTI\automatic\modules\script_loading.py:29 in load_module                                                  │
│                                                                                                                      │
│   28 │   │   │   │   with contextlib.redirect_stdout(io.StringIO()) as stdout:                                       │
│ ❱ 29 │   │   │   │   │   module_spec.loader.exec_module(module)                                                      │
│   30 │   │   │   setup_logging() # reset since scripts can hijaack logging                                           │
│ in exec_module:883                                                                                                   │
│ in _call_with_frames_removed:241                                                                                     │
│                                                                                                                      │
│ E:\GitHub\TTI\automatic\extensions\sd-forge-layerdiffuse\scripts\forge_layerdiffusion.py:11 in <module>              │
│                                                                                                                      │
│    10 from lib_layerdiffusion.enums import ResizeMode                                                                │
│ ❱  11 from lib_layerdiffusion.utils import rgba2rgbfp32, to255unit8, crop_and_resize_image, forge_clip_encode        │
│    12 from enum import Enum                                                                                          │
│                                                                                                                      │
│ E:\GitHub\TTI\automatic\extensions\sd-forge-layerdiffuse\lib_layerdiffusion\utils.py:3 in <module>                   │
│                                                                                                                      │
│    2 from lib_layerdiffusion.enums import ResizeMode                                                                 │
│ ❱  3 from ldm_patched.modules import model_management                                                                │
│    4 import cv2                                                                                                      │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
ModuleNotFoundError: No module named 'ldm_patched'

Version Platform Description

Python 3.10.11 on Windows Version: app=sd.next updated=2024-05-13 hash=58304dcf branch=dev url=https://github.com/vladmandic/automatic/tree/dev Updating main repository Upgraded to version: 58304dcf Mon May 13 17:54:02 2024 -0400 Platform: arch=AMD64 cpu=AMD64 Family 25 Model 33 Stepping 2, AuthenticAMD system=Windows release=Windows-10-10.0.22631-SP0 python=3.10.11 nVidia CUDA toolkit detected: nvidia-smi present Load packages: {'torch': '2.2.1+cu121', 'diffusers': '0.27.2', 'gradio': '3.43.2'} Device: device=NVIDIA GeForce RTX 3060 n=1 arch=sm_90 cap=(8, 6) cuda=12.1 cudnn=8801 driver=552.22

URL link of the extension

https://github.com/layerdiffusion/sd-forge-layerdiffuse

URL link of the issue reported in the extension repository

No response

Acknowledgements

• [X] I have read the above and searched for existing issues