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

inpainting fix per PR #1218

Browse Source 
- This is a merge of the final version of PR #1218 "Inpainting
  Improvements"

  Various merge conflicts made it easier to commit directly.

Author: Kyle0654
Co-Author: lstein
This commit is contained in:
Lincoln Stein 2022-10-23 22:52:32 -04:00
parent 27f0f3e52b
commit 543464182f
2 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
configs/models.yaml
View File

@ -8,15 +8,16 @@
stable-diffusion-1.4: stable-diffusion-1.4:
config: configs/stable-diffusion/v1-inference.yaml config: configs/stable-diffusion/v1-inference.yaml
weights: models/ldm/stable-diffusion-v1/model.ckpt weights: models/ldm/stable-diffusion-v1/model.ckpt
vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt # vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
description: Stable Diffusion inference model version 1.4 description: Stable Diffusion inference model version 1.4
default: true
width: 512 width: 512
height: 512 height: 512
default: true default: true
stable-diffusion-1.5: stable-diffusion-1.5:
config: configs/stable-diffusion/v1-inference.yaml config: configs/stable-diffusion/v1-inference.yaml
weights: models/ldm/stable-diffusion-v1/v1-5-pruned-emaonly.ckpt weights: models/ldm/stable-diffusion-v1/v1-5-pruned-emaonly.ckpt
# vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
description: Stable Diffusion inference model version 1.5 description: Stable Diffusion inference model version 1.5
width: 512 width: 512
height: 512 height: 512
vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt

2
ldm/invoke/generator/inpaint.py
View File

@ -109,7 +109,7 @@ class Inpaint(Img2Img):
return make_image return make_image
def sample_to_image(self, samples)->Image: def sample_to_image(self, samples)->Image.Image:
gen_result = super().sample_to_image(samples).convert('RGB') gen_result = super().sample_to_image(samples).convert('RGB')
if self.pil_image is None or self.pil_mask is None: if self.pil_image is None or self.pil_mask is None: