AIAny
AI Image2025
Icon for item

workflow_templates (ComfyUI workflow templates)

Provides curated ComfyUI workflow templates and subgraph blueprints that package reusable node graphs, preview assets, and publishing pipelines for image/video generation. Includes a browsable Astro site with i18n, CI-driven sync/publish scripts, and PyPI packaging for easy distribution.

Introduction

Sharing and re-using ComfyUI workflows is often ad-hoc and error-prone; this repository centralizes templates, subgraph blueprints, preview assets, and automation so authors can publish reproducible workflows that users can browse, preview, and install without manual asset wrangling.

What Sets It Apart
  • Standardized template format and bundles: templates live under templates/ and are packaged per media type into Python packages (package-per-media) so consumers can install only what they need. This reduces friction when distributing many small workflows.
  • Embedded model metadata and compatibility checks: workflows can embed model download links, hashes, and node-version hints so a user can run a template without hunting for external files; CI validates JSON/schema/bundle consistency to catch regressions early.
  • Site + automation for discoverability: an independent Astro static site provides searchable previews, AI-generated descriptions, and i18n (11 languages). GitHub Actions automate daily rebuilds, previews, and PyPI publishing, keeping the index and packaged artifacts in sync.
Who It's For & Trade-offs

Great fit if you build or curate ComfyUI workflows and want repeatable distribution, preview thumbnails, and integrated packaging for consumers. It streamlines adding templates or blueprints and enforces validation before publishing. Look elsewhere if you only need ad-hoc local workflows (no packaging) or require a different workflow format—this repo assumes the ComfyUI subgraph/workflow JSON format and a CI-driven package release model, which adds maintenance overhead for small one-off examples.

Where It Fits

Use this repo as the canonical hub for reusable ComfyUI templates and subgraph blueprints that should be discoverable, previewable, and publishable (via PyPI and a static site). It complements example repositories and documentation by providing the distribution and validation infrastructure that scales across many templates and media types.

Information

  • Websitegithub.com
  • OrganizationsComfy-Org
  • Published date2025/02/28

More Items

Hugging Face
AI Video2026

LoRA adapters for MiniMax H3 that sharpen and enhance videos in ComfyUI by conditioning on source clips via guide latents for pixel-level alignment. Designed mainly for ref2va as a second-pass sharpening tool, includes a ComfyUI workflow and example before/after clips; requires aligned guide clips at the target resolution and valid clip lengths.

Hugging Face
AI Video2026

Replaces a character in a video using a single repainted frame from the same clip and propagates that edit across the shot while preserving motion, camera and lighting; requires no pose estimator, segmentation, face tracker or text prompt. Key facts: a 33.1B MiniMax-H3 finetune, DMD-distilled to three forward passes, 124 frames in ~26s on one B200 GPU.

Hugging Face
AI Video2026

Generates short multimodal videos from text, images, or reference clips using a fine-tuned MiniMax‑H3 fusion model; improves HDR clarity, motion fluidity, distant-face fidelity and VFX while preserving MiniMax‑H3’s prompt/style behavior. Best used via ComfyUI.