Mirror/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2024-06-07 21:20:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

remove type annotations in new code because presumably they don't work in 3.7

Browse Source
This commit is contained in:
AUTOMATIC 2022-10-06 00:09:32 +03:00
parent f8e41a96bb
commit 20f8ec877a
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
modules/prompt_parser.py
View File

@ -175,14 +175,14 @@ def get_multicond_prompt_list(prompts):
class ComposableScheduledPromptConditioning: class ComposableScheduledPromptConditioning:
def __init__(self, schedules, weight=1.0): def __init__(self, schedules, weight=1.0):
self.schedules: list[ScheduledPromptConditioning] = schedules self.schedules = schedules # : list[ScheduledPromptConditioning]
self.weight: float = weight self.weight: float = weight
class MulticondLearnedConditioning: class MulticondLearnedConditioning:
def __init__(self, shape, batch): def __init__(self, shape, batch):
self.shape: tuple = shape # the shape field is needed to send this object to DDIM/PLMS self.shape: tuple = shape # the shape field is needed to send this object to DDIM/PLMS
self.batch: list[list[ComposableScheduledPromptConditioning]] = batch self.batch = batch # : list[list[ComposableScheduledPromptConditioning]]
def get_multicond_learned_conditioning(model, prompts, steps) -> MulticondLearnedConditioning: def get_multicond_learned_conditioning(model, prompts, steps) -> MulticondLearnedConditioning:
@ -203,7 +203,7 @@ def get_multicond_learned_conditioning(model, prompts, steps) -> MulticondLearne
return MulticondLearnedConditioning(shape=(len(prompts),), batch=res) return MulticondLearnedConditioning(shape=(len(prompts),), batch=res)
def reconstruct_cond_batch(c: list[list[ScheduledPromptConditioning]], current_step): def reconstruct_cond_batch(c, current_step): # c: list[list[ScheduledPromptConditioning]]
param = c[0][0].cond param = c[0][0].cond
res = torch.zeros((len(c),) + param.shape, device=param.device, dtype=param.dtype) res = torch.zeros((len(c),) + param.shape, device=param.device, dtype=param.dtype)
for i, cond_schedule in enumerate(c): for i, cond_schedule in enumerate(c):