Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(events): fix denoise progress percentage

Browse Source 
- Restore calculation of step percentage but in the backend instead of client
- Simplify signatures for denoise progress event callbacks
- Clean up `step_callback.py` (types, do not recreate constant matrix on every step, formatting)
This commit is contained in:
psychedelicious
2024-04-01 18:16:33 +11:00
parent ec4f10aed3
commit 0f733c42fc
3 changed files with 59 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

93
invokeai/app/util/step_callback.py
View File

@ -1,4 +1,4 @@
from typing import TYPE_CHECKING, Callable
from typing import TYPE_CHECKING, Callable, Optional
import torch
from PIL import Image
@ -13,8 +13,36 @@ if TYPE_CHECKING:
from invokeai.app.services.events.events_base import EventServiceBase
from invokeai.app.services.shared.invocation_context import InvocationContextData
# fast latents preview matrix for sdxl
# generated by @StAlKeR7779
SDXL_LATENT_RGB_FACTORS = [
# R G B
[0.3816, 0.4930, 0.5320],
[-0.3753, 0.1631, 0.1739],
[0.1770, 0.3588, -0.2048],
[-0.4350, -0.2644, -0.4289],
]
SDXL_SMOOTH_MATRIX = [
[0.0358, 0.0964, 0.0358],
[0.0964, 0.4711, 0.0964],
[0.0358, 0.0964, 0.0358],
]
def sample_to_lowres_estimated_image(samples, latent_rgb_factors, smooth_matrix=None):
# origingally adapted from code by @erucipe and @keturn here:
# https://discuss.huggingface.co/t/decoding-latents-to-rgb-without-upscaling/23204/7
# these updated numbers for v1.5 are from @torridgristle
SD1_5_LATENT_RGB_FACTORS = [
# R G B
[0.3444, 0.1385, 0.0670], # L1
[0.1247, 0.4027, 0.1494], # L2
[-0.3192, 0.2513, 0.2103], # L3
[-0.1307, -0.1874, -0.7445], # L4
]
def sample_to_lowres_estimated_image(
samples: torch.Tensor, latent_rgb_factors: torch.Tensor, smooth_matrix: Optional[torch.Tensor] = None
):
latent_image = samples[0].permute(1, 2, 0) @ latent_rgb_factors
if smooth_matrix is not None:
@ -47,64 +75,12 @@ def stable_diffusion_step_callback(
else:
sample = intermediate_state.latents
# TODO: This does not seem to be needed any more?
# # txt2img provides a Tensor in the step_callback
# # img2img provides a PipelineIntermediateState
# if isinstance(sample, PipelineIntermediateState):
# # this was an img2img
# print('img2img')
# latents = sample.latents
# step = sample.step
# else:
# print('txt2img')
# latents = sample
# step = intermediate_state.step
# TODO: only output a preview image when requested
if base_model in [BaseModelType.StableDiffusionXL, BaseModelType.StableDiffusionXLRefiner]:
# fast latents preview matrix for sdxl
# generated by @StAlKeR7779
sdxl_latent_rgb_factors = torch.tensor(
[
# R G B
[0.3816, 0.4930, 0.5320],
[-0.3753, 0.1631, 0.1739],
[0.1770, 0.3588, -0.2048],
[-0.4350, -0.2644, -0.4289],
],
dtype=sample.dtype,
device=sample.device,
)
sdxl_smooth_matrix = torch.tensor(
[
[0.0358, 0.0964, 0.0358],
[0.0964, 0.4711, 0.0964],
[0.0358, 0.0964, 0.0358],
],
dtype=sample.dtype,
device=sample.device,
)
sdxl_latent_rgb_factors = torch.tensor(SDXL_LATENT_RGB_FACTORS, dtype=sample.dtype, device=sample.device)
sdxl_smooth_matrix = torch.tensor(SDXL_SMOOTH_MATRIX, dtype=sample.dtype, device=sample.device)
image = sample_to_lowres_estimated_image(sample, sdxl_latent_rgb_factors, sdxl_smooth_matrix)
else:
# origingally adapted from code by @erucipe and @keturn here:
# https://discuss.huggingface.co/t/decoding-latents-to-rgb-without-upscaling/23204/7
# these updated numbers for v1.5 are from @torridgristle
v1_5_latent_rgb_factors = torch.tensor(
[
# R G B
[0.3444, 0.1385, 0.0670], # L1
[0.1247, 0.4027, 0.1494], # L2
[-0.3192, 0.2513, 0.2103], # L3
[-0.1307, -0.1874, -0.7445], # L4
],
dtype=sample.dtype,
device=sample.device,
)
v1_5_latent_rgb_factors = torch.tensor(SD1_5_LATENT_RGB_FACTORS, dtype=sample.dtype, device=sample.device)
image = sample_to_lowres_estimated_image(sample, v1_5_latent_rgb_factors)
(width, height) = image.size
@ -116,7 +92,6 @@ def stable_diffusion_step_callback(
events.emit_invocation_denoise_progress(
context_data.queue_item,
context_data.invocation,
intermediate_state.step,
intermediate_state.total_steps * intermediate_state.order,
intermediate_state,
ProgressImage(dataURL=dataURL, width=width, height=height),
)