diff options
Diffstat (limited to 'modules/processing.py')
| -rw-r--r-- | modules/processing.py | 19 |
1 files changed, 9 insertions, 10 deletions
diff --git a/modules/processing.py b/modules/processing.py index ae58b108..43cb763f 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -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
@@ -795,6 +795,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if getattr(samples_ddim, 'already_decoded', False):
x_samples_ddim = samples_ddim
else:
+ p.extra_generation_params['VAE Decoder'] = opts.sd_vae_decode_method
x_samples_ddim = decode_latent_batch(p.sd_model, samples_ddim, target_device=devices.cpu, check_for_nans=True)
x_samples_ddim = torch.stack(x_samples_ddim).float()
@@ -1135,11 +1136,10 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): batch_images.append(image)
decoded_samples = torch.from_numpy(np.array(batch_images))
- decoded_samples = decoded_samples.to(shared.device)
- decoded_samples = 2. * decoded_samples - 1.
decoded_samples = decoded_samples.to(shared.device, dtype=devices.dtype_vae)
- samples = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(decoded_samples))
+ self.extra_generation_params['VAE Encoder'] = opts.sd_vae_encode_method
+ samples = images_tensor_to_samples(decoded_samples, approximation_indexes.get(opts.sd_vae_encode_method))
image_conditioning = self.img2img_image_conditioning(decoded_samples, samples)
@@ -1374,10 +1374,9 @@ 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)
- image = 2. * image - 1.
image = image.to(shared.device, dtype=devices.dtype_vae)
-
- self.init_latent = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image))
+ self.extra_generation_params['VAE Encoder'] = opts.sd_vae_encode_method
+ self.init_latent = images_tensor_to_samples(image, approximation_indexes.get(opts.sd_vae_encode_method), self.sd_model)
devices.torch_gc()
if self.resize_mode == 3:
|