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

[Hacktoberfest]Fixing issues #5241 (#5255)

Browse Source 
* Update pipeline_wuerstchen_prior.py

* prior_num_inference_steps updated

* height, width, num_inference_steps, and guidance_scale synced

* parameters synced

* latent_mean, latent_std, and resolution_multiple synced

* prior_num_inference_steps changed

* Formatted pipeline_wuerstchen_prior.py

* Update src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_prior.py

---------

Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
This commit is contained in:
vedant2003
2023-10-07 02:49:38 +05:30
committed by GitHub
parent 016866792d
commit dd25ef5679
3 changed files with 13 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen.py
View File

@@ -213,13 +213,13 @@ class WuerstchenDecoderPipeline(DiffusionPipeline):
Image Embeddings either extracted from an image or generated by a Prior Model.
prompt (`str` or `List[str]`):
The prompt or prompts to guide the image generation.
num_inference_steps (`int`, *optional*, defaults to 30):
num_inference_steps (`int`, *optional*, defaults to 12):
The number of denoising steps. More denoising steps usually lead to a higher quality image at the
expense of slower inference.
timesteps (`List[int]`, *optional*):
Custom timesteps to use for the denoising process. If not defined, equal spaced `num_inference_steps`
timesteps are used. Must be in descending order.
guidance_scale (`float`, *optional*, defaults to 4.0):
guidance_scale (`float`, *optional*, defaults to 0.0):
Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
`decoder_guidance_scale` is defined as `w` of equation 2. of [Imagen
Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting

2
src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_combined.py
View File

@@ -194,7 +194,7 @@ class WuerstchenCombinedPipeline(DiffusionPipeline):
Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting
`prior_guidance_scale > 1`. Higher guidance scale encourages to generate images that are closely linked
to the text `prompt`, usually at the expense of lower image quality.
prior_num_inference_steps (`Union[int, Dict[float, int]]`, *optional*, defaults to 30):
prior_num_inference_steps (`Union[int, Dict[float, int]]`, *optional*, defaults to 60):
The number of prior denoising steps. More denoising steps usually lead to a higher quality image at the
expense of slower inference. For more specific timestep spacing, you can pass customized
`prior_timesteps`

14
src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_prior.py
View File

@@ -82,6 +82,12 @@ class WuerstchenPriorPipeline(DiffusionPipeline):
[CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
scheduler ([`DDPMWuerstchenScheduler`]):
A scheduler to be used in combination with `prior` to generate image embedding.
latent_mean ('float', *optional*, defaults to 42.0):
Mean value for latent diffusers.
latent_std ('float', *optional*, defaults to 1.0):
Standard value for latent diffusers.
resolution_multiple ('float', *optional*, defaults to 42.67):
Default resolution for multiple images generated.
"""
model_cpu_offload_seq = "text_encoder->prior"
@@ -282,17 +288,17 @@ class WuerstchenPriorPipeline(DiffusionPipeline):
Args:
prompt (`str` or `List[str]`):
The prompt or prompts to guide the image generation.
height (`int`, *optional*, defaults to 512):
height (`int`, *optional*, defaults to 1024):
The height in pixels of the generated image.
width (`int`, *optional*, defaults to 512):
width (`int`, *optional*, defaults to 1024):
The width in pixels of the generated image.
num_inference_steps (`int`, *optional*, defaults to 30):
num_inference_steps (`int`, *optional*, defaults to 60):
The number of denoising steps. More denoising steps usually lead to a higher quality image at the
expense of slower inference.
timesteps (`List[int]`, *optional*):
Custom timesteps to use for the denoising process. If not defined, equal spaced `num_inference_steps`
timesteps are used. Must be in descending order.
guidance_scale (`float`, *optional*, defaults to 4.0):
guidance_scale (`float`, *optional*, defaults to 8.0):
Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
`decoder_guidance_scale` is defined as `w` of equation 2. of [Imagen
Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting