AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

Fix depth pipeline "input/weight type should be the same" error at fp16 (#8321)

Browse Source 
Fix "input/weight type should be the same"

Co-authored-by: YiYi Xu <yixu310@gmail.com>
This commit is contained in:
Jonah
2024-05-30 20:59:49 -03:00
committed by GitHub
parent 352d96eb82
commit 05be622b1c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_depth2img.py
View File

@@ -546,7 +546,7 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
if depth_map is None:
pixel_values = self.feature_extractor(images=image, return_tensors="pt").pixel_values
pixel_values = pixel_values.to(device=device)
pixel_values = pixel_values.to(device=device, dtype=dtype)
# The DPT-Hybrid model uses batch-norm layers which are not compatible with fp16.
# So we use `torch.autocast` here for half precision inference.
if torch.backends.mps.is_available():