mirror of
https://github.com/vladmandic/automatic
synced 2026-09-17 08:19:11 +02:00
Add two new ControlNet models for SDXL
This PR adds two new ControlNet models made by HF user xinsir: - New OpenPose model - New Canny model Both outperform the standard CN models and they also affect generation much less. As a plus, the OpenPose model is half the size of the one used by SD.Next.
This commit is contained in:
@@ -50,6 +50,8 @@ predefined_sdxl = {
|
||||
'Depth Zoe XL': 'diffusers/controlnet-zoe-depth-sdxl-1.0',
|
||||
'Depth Mid XL': 'diffusers/controlnet-depth-sdxl-1.0-mid',
|
||||
'OpenPose XL': 'thibaud/controlnet-openpose-sdxl-1.0',
|
||||
'xinsir-controlnet-openpose-sdxl': 'xinsir/controlnet-openpose-sdxl-1.0',
|
||||
'xinsir-controlnet-canny': 'xinsir/controlnet-canny-sdxl-1.0'
|
||||
# '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',
|
||||
|
||||
Reference in New Issue
Block a user