kanshan/diffusers
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

small bugfix at StableDiffusionDepth2ImgPipeline call to check_inputs and batch size calculation (#2423)

Browse Source 
small bugfix in call to check_inputs and batch size calculation

Co-authored-by: mishka <gartsocial@gmail.com>
This commit is contained in:
Michael Gartsbein
2023-02-20 12:55:47 +02:00
committed by GitHub
parent 8f1fe75b4c
commit f3fac68c55
1 changed files with 15 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_depth2img.py
+15 -2
View File
@@ -587,13 +587,26 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline):
(nsfw) content, according to the `safety_checker`. (nsfw) content, according to the `safety_checker`.
""" """
# 1. Check inputs # 1. Check inputs
self.check_inputs(prompt, strength, callback_steps) self.check_inputs(
prompt,
strength,
callback_steps,
negative_prompt=negative_prompt,
prompt_embeds=prompt_embeds,
negative_prompt_embeds=negative_prompt_embeds,
)
if image is None: if image is None:
raise ValueError("`image` input cannot be undefined.") raise ValueError("`image` input cannot be undefined.")
# 2. Define call parameters # 2. Define call parameters
batch_size = 1 if isinstance(prompt, str) else len(prompt) if prompt is not None and isinstance(prompt, str):
batch_size = 1
elif prompt is not None and isinstance(prompt, list):
batch_size = len(prompt)
else:
batch_size = prompt_embeds.shape[0]
device = self._execution_device device = self._execution_device
# here `guidance_scale` is defined analog to the guidance weight `w` of equation (2) # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
# of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1` # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`