2026-06-08 19:32:04 +03:00
2026-06-11 03:36:26 +03:00
2026-06-08 19:32:04 +03:00
2026-06-08 19:32:04 +03:00
2026-06-08 19:32:04 +03:00
2026-06-08 19:32:04 +03:00
2026-06-08 19:32:04 +03:00
2026-06-08 19:32:04 +03:00
2026-06-08 19:32:04 +03:00
2026-06-08 19:32:04 +03:00
2026-06-08 19:32:04 +03:00

ComfyUI Stat-Imp Nodes

Clean, MIT-licensed nodes for Deforum-style animation loops in ComfyUI. This release ships three nodes: a depth-aware 3D camera warp and two color-coherence nodes (a fixed-anchor matcher and a rolling/EMA matcher) that stop the feedback loop's color from drifting into neon "acid".

Pure torch — no extra Python dependencies. See NODES.md for the full per-node reference (inputs, outputs, motion directions, tuning guidance).

Install

Manual / git: clone into your ComfyUI custom-nodes folder, then restart ComfyUI and hard-refresh the browser:

cd ComfyUI/custom_nodes
git clone https://github.com/Statistical-Impossibility/comfyui-Stat-Imp-nodes

The nodes appear under the Stat-Imp / Deforum menu group.

How to use

These nodes are building blocks for a Deforum-style 3D animation loop. A ready-to-run example workflow is included:

➡️ workflows/deforum_SDXL_Distilled.json — a full depth-warp + color-coherence animation loop for SDXL Turbo / Lightning / Hyper.

Open it in ComfyUI, pick a distilled SDXL checkpoint, and queue. The embedded note explains the inputs and settings.

Credits

This pack stands on the original Deforum work — full credit to its authors:

  • Deforum (Stable Diffusion) — the original animation engine. The camera math here is a forward port of its transform_image_3d, and the color matcher is a clean-room reimplementation of its maintain_colors (helpers/colors.py).
  • Deforum-Comfy-Nodes — the main ComfyUI Deforum harness and node pack (ForLoop, schedules, Set/Get bus).
  • py3d_tools (BSD) — projection conventions; py3d_tools is a stripped subset of PyTorch3D.

Camera geometry is ported exactly; color coherence is a pure-torch reimplementation (quantile histogram match, no skimage/cv2). This wrapper and the pure-torch reimplementations are MIT (see LICENSE).

S
Description
No description provided
Readme MIT
250 KiB
Languages
Python 100%