Mirrors
/
stable-diffusion-webui
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

replace get_first_stage_encoding

This commit is contained in:
Kohaku-Blueleaf 2023-08-04 18:23:14 +08:00
parent 073342c887
commit 21000f13a1
1 changed files with 5 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
modules/processing.py
View File

@ -16,6 +16,7 @@ from typing import Any, Dict, List
import modules.sd_hijack
from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, extra_networks, sd_vae_approx, scripts, sd_samplers_common, sd_unet, errors
from modules.sd_hijack import model_hijack
from modules.sd_samplers_common import images_tensor_to_samples, decode_first_stage, approximation_indexes
from modules.shared import opts, cmd_opts, state
import modules.shared as shared
import modules.paths as paths
@ -30,7 +31,6 @@ from ldm.models.diffusion.ddpm import LatentDepth2ImageDiffusion
from einops import repeat, rearrange
from blendmodes.blend import blendLayers, BlendType
decode_first_stage = sd_samplers_common.decode_first_stage
# some of those options should not be changed at all because they would break the model, so I removed them from options.
opt_C = 4
@ -84,7 +84,7 @@ def txt2img_image_conditioning(sd_model, x, width, height):
# The "masked-image" in this case will just be all zeros since the entire image is masked.
image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
image_conditioning = sd_model.get_first_stage_encoding(sd_model.encode_first_stage(image_conditioning))
image_conditioning = images_tensor_to_samples(image_conditioning, approximation_indexes.get(opts.sd_vae_encode_method))
# Add the fake full 1s mask to the first dimension.
image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
@ -203,7 +203,7 @@ class StableDiffusionProcessing:
midas_in = torch.from_numpy(transformed["midas_in"][None, ...]).to(device=shared.device)
midas_in = repeat(midas_in, "1 ... -> n ...", n=self.batch_size)
conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image))
conditioning_image = images_tensor_to_samples(source_image*0.5+0.5, approximation_indexes.get(opts.sd_vae_encode_method))
conditioning = torch.nn.functional.interpolate(
self.sd_model.depth_model(midas_in),
size=conditioning_image.shape[2:],
@ -216,7 +216,7 @@ class StableDiffusionProcessing:
return conditioning
def edit_image_conditioning(self, source_image):
conditioning_image = self.sd_model.encode_first_stage(source_image).mode()
conditioning_image = images_tensor_to_samples(source_image*0.5+0.5, approximation_indexes.get(opts.sd_vae_encode_method))
return conditioning_image
@ -1099,9 +1099,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
decoded_samples = torch.from_numpy(np.array(batch_images))
decoded_samples = decoded_samples.to(shared.device)
decoded_samples = 2. * decoded_samples - 1.
samples = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(decoded_samples))
samples = images_tensor_to_samples(decoded_samples, approximation_indexes.get(opts.sd_vae_encode_method))
image_conditioning = self.img2img_image_conditioning(decoded_samples, samples)
@ -1339,7 +1338,6 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
raise RuntimeError(f"bad number of images passed: {len(imgs)}; expecting {self.batch_size} or less")
image = torch.from_numpy(batch_images)
from modules.sd_samplers_common import images_tensor_to_samples, approximation_indexes
self.init_latent = images_tensor_to_samples(image, approximation_indexes.get(opts.sd_vae_encode_method), self.sd_model)
devices.torch_gc()