ZImageTurboPiDv2
+Color transfer from lora image as PiD tends to raise the gamma
+Optional SageAttention
+ModelSampling shift to PiD model
Update your ComfyUI for PixelDiT support
For models/text encoder https://huggingface.co/Comfy-Org/PixelDiT
INT8 Models https://civitai.red/models/2662932/pid-int8
PiD reformulates the latent-to-pixel decoder as a conditional pixel-space diffusion model, unifying decoding and upsampling into a single generative module. It denoises directly in high-resolution pixel space and produces a super-resolved image in one pass. This repository hosts the released decoder checkpoints, plus the encoder/decoder ("VAE") weights they depend on.
This workflow takes a ZImageTurbo/ZImage generation latent from 512x512>2048x2048/1024x1024>4096x4096 or 16:9, 4:3, 3:4 aspect ratios.
RTX 3060 12gb + 32gb ram
60 seconds upscale+decode for 1024 model 768x1024>3072x4096
8 seconds upscale+decode for 512 model 432x576>1728x2304