98 lines
3.6 KiB
Python
98 lines
3.6 KiB
Python
import torch
|
|
from PIL import Image
|
|
import struct
|
|
import numpy as np
|
|
from comfy.cli_args import args, LatentPreviewMethod
|
|
from comfy.taesd.taesd import TAESD
|
|
import comfy.model_management
|
|
import folder_paths
|
|
import comfy.utils
|
|
import logging
|
|
|
|
MAX_PREVIEW_RESOLUTION = 512
|
|
|
|
class LatentPreviewer:
|
|
def decode_latent_to_preview(self, x0):
|
|
pass
|
|
|
|
def decode_latent_to_preview_image(self, preview_format, x0):
|
|
preview_image = self.decode_latent_to_preview(x0)
|
|
return ("JPEG", preview_image, MAX_PREVIEW_RESOLUTION)
|
|
|
|
class TAESDPreviewerImpl(LatentPreviewer):
|
|
def __init__(self, taesd):
|
|
self.taesd = taesd
|
|
|
|
def decode_latent_to_preview(self, x0):
|
|
x_sample = self.taesd.decode(x0[:1])[0].detach()
|
|
x_sample = 255. * torch.clamp((x_sample + 1.0) / 2.0, min=0.0, max=1.0)
|
|
x_sample = np.moveaxis(x_sample.to(device="cpu", dtype=torch.uint8, non_blocking=comfy.model_management.device_supports_non_blocking(x_sample.device)).numpy(), 0, 2)
|
|
|
|
preview_image = Image.fromarray(x_sample)
|
|
return preview_image
|
|
|
|
|
|
class Latent2RGBPreviewer(LatentPreviewer):
|
|
def __init__(self, latent_rgb_factors):
|
|
self.latent_rgb_factors = torch.tensor(latent_rgb_factors, device="cpu")
|
|
|
|
def decode_latent_to_preview(self, x0):
|
|
self.latent_rgb_factors = self.latent_rgb_factors.to(dtype=x0.dtype, device=x0.device)
|
|
latent_image = x0[0].permute(1, 2, 0) @ self.latent_rgb_factors
|
|
|
|
latents_ubyte = (((latent_image + 1) / 2)
|
|
.clamp(0, 1) # change scale from -1..1 to 0..1
|
|
.mul(0xFF) # to 0..255
|
|
).to(device="cpu", dtype=torch.uint8, non_blocking=comfy.model_management.device_supports_non_blocking(latent_image.device))
|
|
|
|
return Image.fromarray(latents_ubyte.numpy())
|
|
|
|
|
|
def get_previewer(device, latent_format):
|
|
previewer = None
|
|
method = args.preview_method
|
|
if method != LatentPreviewMethod.NoPreviews:
|
|
# TODO previewer methods
|
|
taesd_decoder_path = None
|
|
if latent_format.taesd_decoder_name is not None:
|
|
taesd_decoder_path = next(
|
|
(fn for fn in folder_paths.get_filename_list("vae_approx")
|
|
if fn.startswith(latent_format.taesd_decoder_name)),
|
|
""
|
|
)
|
|
taesd_decoder_path = folder_paths.get_full_path("vae_approx", taesd_decoder_path)
|
|
|
|
if method == LatentPreviewMethod.Auto:
|
|
method = LatentPreviewMethod.Latent2RGB
|
|
|
|
if method == LatentPreviewMethod.TAESD:
|
|
if taesd_decoder_path:
|
|
taesd = TAESD(None, taesd_decoder_path).to(device)
|
|
previewer = TAESDPreviewerImpl(taesd)
|
|
else:
|
|
logging.warning("Warning: TAESD previews enabled, but could not find models/vae_approx/{}".format(latent_format.taesd_decoder_name))
|
|
|
|
if previewer is None:
|
|
if latent_format.latent_rgb_factors is not None:
|
|
previewer = Latent2RGBPreviewer(latent_format.latent_rgb_factors)
|
|
return previewer
|
|
|
|
def prepare_callback(model, steps, x0_output_dict=None):
|
|
preview_format = "JPEG"
|
|
if preview_format not in ["JPEG", "PNG"]:
|
|
preview_format = "JPEG"
|
|
|
|
previewer = get_previewer(model.load_device, model.model.latent_format)
|
|
|
|
pbar = comfy.utils.ProgressBar(steps)
|
|
def callback(step, x0, x, total_steps):
|
|
if x0_output_dict is not None:
|
|
x0_output_dict["x0"] = x0
|
|
|
|
preview_bytes = None
|
|
if previewer:
|
|
preview_bytes = previewer.decode_latent_to_preview_image(preview_format, x0)
|
|
pbar.update_absolute(step + 1, total_steps, preview_bytes)
|
|
return callback
|
|
|