Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: SDXL Refiner not working properly with Inpainting

Browse Source
This commit is contained in:
blessedcoolant
2024-04-09 07:19:16 +05:30
committed by psychedelicious
parent 381b41a56e
commit fd1f240853
3 changed files with 5 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
invokeai/backend/stable_diffusion/diffusers_pipeline.py
View File

@ -336,9 +336,6 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
).to(device=orig_latents.device, dtype=orig_latents.dtype)
latents = self.scheduler.add_noise(latents, noise, batched_t)
latents = torch.lerp(
orig_latents, latents.to(dtype=orig_latents.dtype), mask.to(dtype=orig_latents.dtype)
)
if is_inpainting_model(self.unet):
if masked_latents is None: