ComfyUI Node: PiD Empty Latent Image
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
PiD
Inputs
pid_ckpt_type
- 2k
- 2kto4k
resolution
- 512x512 (1:1)
- 576x432 (4:3)
- 432x576 (3:4)
- 624x416 (3:2)
- 416x624 (2:3)
- 672x384 (16:9)
- 384x672 (9:16)
- 784x336 (21:9)
- 336x784 (9:21)
- 1024x1024 (1:1)
- 1024x768 (4:3)
- 768x1024 (3:4)
- 1008x672 (3:2)
- 672x1008 (2:3)
- 1024x576 (16:9)
- 576x1024 (9:16)
- 1008x432 (21:9)
- 432x1008 (9:21)
batch_size INT
backbone
- zimage
- zimage-turbo
- flux
- flux2
- flux2-klein-4b
- flux2-klein-9b
- sd3
- sdxl
- qwenimage
- qwenimage-2512
Outputs
LATENT
Extension: ComfyUI-PiD
ComfyUI custom nodes for NVIDIA PiD pixel diffusion decoding with VRAM offload support.
Authored by Merserk
Looking for a different node?
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.