github/InvokeAI
1
1
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI.git synced 2026-04-23 03:00:31 -04:00
Code Issues Packages Projects Releases Wiki Activity

Enable correct probing of LoRA latent-consistency/lcm-lora-sdxl (#5449)

Browse Source 
- Closes #5435

Co-authored-by: Lincoln Stein <lstein@gmail.com>
This commit is contained in:
Lincoln Stein
2024-01-08 17:18:26 -05:00
committed by GitHub
parent d86d7e5c33
commit 7269c9f02e
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
invokeai/backend/model_management/model_probe.py
View File

@@ -370,6 +370,8 @@ class LoRACheckpointProbe(CheckpointProbeBase):
return BaseModelType.StableDiffusion1
elif token_vector_length == 1024:
return BaseModelType.StableDiffusion2
elif token_vector_length == 1280:
return BaseModelType.StableDiffusionXL # recognizes format at https://civitai.com/models/224641
elif token_vector_length == 2048:
return BaseModelType.StableDiffusionXL
else: