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

Fix typos (#978)

Browse Source
This commit is contained in:
Yuta Hayashibe
2022-10-26 22:32:47 +09:00
committed by GitHub
parent d7d6841406
commit cc436087d3
5 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/community/README.md
View File

@@ -355,7 +355,7 @@ generator = th.Generator("cuda").manual_seed(0)
seed = 0
prompt = "a forest | a camel"
weights = " 1 | 1" # Equal weight to each prompt. Cna be negative
weights = " 1 | 1" # Equal weight to each prompt. Can be negative
images = []
for i in range(4):

4
examples/community/composable_stable_diffusion.py
View File

@@ -133,7 +133,7 @@ class ComposableStableDiffusionPipeline(DiffusionPipeline):
tensor will ge generated by sampling using the supplied random `generator`.
output_type (`str`, *optional*, defaults to `"pil"`):
The output format of the generate image. Choose between
[PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `nd.array`.
[PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
return_dict (`bool`, *optional*, defaults to `True`):
Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
plain tuple.
@@ -264,7 +264,7 @@ class ComposableStableDiffusionPipeline(DiffusionPipeline):
self.scheduler.set_timesteps(num_inference_steps, **extra_set_kwargs)
# if we use LMSDiscreteScheduler, let's make sure latents are mulitplied by sigmas
# if we use LMSDiscreteScheduler, let's make sure latents are multiplied by sigmas
if isinstance(self.scheduler, LMSDiscreteScheduler):
latents = latents * self.scheduler.sigmas[0]

6
examples/community/lpw_stable_diffusion.py
View File

@@ -40,7 +40,7 @@ re_attention = re.compile(
def parse_prompt_attention(text):
"""
Parses a string with attention tokens and returns a list of pairs: text and its assoicated weight.
Parses a string with attention tokens and returns a list of pairs: text and its associated weight.
Accepted tokens are:
(abc) - increases attention to abc by a multiplier of 1.1
(abc:3.12) - increases attention to abc by a multiplier of 3.12
@@ -237,9 +237,9 @@ def get_weighted_text_embeddings(
r"""
Prompts can be assigned with local weights using brackets. For example,
prompt 'A (very beautiful) masterpiece' highlights the words 'very beautiful',
and the embedding tokens corresponding to the words get multipled by a constant, 1.1.
and the embedding tokens corresponding to the words get multiplied by a constant, 1.1.
Also, to regularize of the embedding, the weighted embedding would be scaled to preserve the origional mean.
Also, to regularize of the embedding, the weighted embedding would be scaled to preserve the original mean.
Args:
pipe (`DiffusionPipeline`):

6
examples/community/lpw_stable_diffusion_onnx.py
View File

@@ -38,7 +38,7 @@ re_attention = re.compile(
def parse_prompt_attention(text):
"""
Parses a string with attention tokens and returns a list of pairs: text and its assoicated weight.
Parses a string with attention tokens and returns a list of pairs: text and its associated weight.
Accepted tokens are:
(abc) - increases attention to abc by a multiplier of 1.1
(abc:3.12) - increases attention to abc by a multiplier of 3.12
@@ -236,9 +236,9 @@ def get_weighted_text_embeddings(
r"""
Prompts can be assigned with local weights using brackets. For example,
prompt 'A (very beautiful) masterpiece' highlights the words 'very beautiful',
and the embedding tokens corresponding to the words get multipled by a constant, 1.1.
and the embedding tokens corresponding to the words get multiplied by a constant, 1.1.
Also, to regularize of the embedding, the weighted embedding would be scaled to preserve the origional mean.
Also, to regularize of the embedding, the weighted embedding would be scaled to preserve the original mean.
Args:
pipe (`DiffusionPipeline`):

4
src/diffusers/pipeline_utils.py
View File

@@ -584,7 +584,7 @@ class DiffusionPipeline(ConfigMixin):
def components(self) -> Dict[str, Any]:
r"""
The `self.compenents` property can be useful to run different pipelines with the same weights and
The `self.components` property can be useful to run different pipelines with the same weights and
configurations to not have to re-allocate memory.
Examples:
@@ -602,7 +602,7 @@ class DiffusionPipeline(ConfigMixin):
```
Returns:
A dictionaly containing all the modules needed to initialize the pipleline.
A dictionaly containing all the modules needed to initialize the pipeline.
"""
components = {k: getattr(self, k) for k in self.config.keys() if not k.startswith("_")}
expected_modules = set(inspect.signature(self.__init__).parameters.keys()) - set(["self"])