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

[SDXL Inpaint] Correct strength default (#4858)

Browse Source
This commit is contained in:
Patrick von Platen
2023-08-31 20:34:33 +02:00
committed by GitHub
parent aedd78767c
commit bbf733ab70
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_inpaint.py
View File

@@ -892,7 +892,7 @@ class StableDiffusionXLInpaintPipeline(DiffusionPipeline, LoraLoaderMixin, FromS
mask_image: PipelineImageInput = None,
height: Optional[int] = None,
width: Optional[int] = None,
strength: float = 1.0,
strength: float = 0.9999,
num_inference_steps: int = 50,
denoising_start: Optional[float] = None,
denoising_end: Optional[float] = None,
@@ -944,7 +944,7 @@ class StableDiffusionXLInpaintPipeline(DiffusionPipeline, LoraLoaderMixin, FromS
The height in pixels of the generated image.
width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
The width in pixels of the generated image.
strength (`float`, *optional*, defaults to 1.):
strength (`float`, *optional*, defaults to 0.9999):
Conceptually, indicates how much to transform the masked portion of the reference `image`. Must be
between 0 and 1. `image` will be used as a starting point, adding more noise to it the larger the
`strength`. The number of denoising steps depends on the amount of noise initially added. When