Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-17 16:24:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

Temporarily change the NoobAI-SDXL OpenPose repo

Browse Source 
The upstream repository by Laxhar Labs does not provide a config.json.
Due to huggingface/diffusers#9976, the single-file safetensors provided
can't be loaded. As such, use a mirror which provides the model in
diffusers format (the model file is in that format already anyway).

Workarounds #3578 for this specific model.
This commit is contained in:
Luca Beltrame
2024-11-20 16:19:38 +01:00
parent b79cd07198
commit 2554870dc8
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/control/units/controlnet.py
+1 -1
View File
@@ -61,7 +61,7 @@ predefined_sdxl = {
'NoobAI Depth XL': 'Eugeoter/noob-sdxl-controlnet-depth',
'NoobAI Normal XL': 'Eugeoter/noob-sdxl-controlnet-normal',
'NoobAI SoftEdge XL': 'Eugeoter/noob-sdxl-controlnet-softedge_hed',
# 'NoobAI OpenPose XL': 'Laxhar/noob_openpose/openpose_pre.safetensors',
'NoobAI OpenPose XL': 'einar77/noob-openpose',
# 'StabilityAI Canny R128': 'stabilityai/control-lora/control-LoRAs-rank128/control-lora-canny-rank128.safetensors',
# 'StabilityAI Depth R128': 'stabilityai/control-lora/control-LoRAs-rank128/control-lora-depth-rank128.safetensors',
# 'StabilityAI Recolor R128': 'stabilityai/control-lora/control-LoRAs-rank128/control-lora-recolor-rank128.safetensors',