Create coherent videos from character, style, and scene references with stable subjects, controlled motion, and sharper detail.

Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning - you still choose inputs, prompts, and settings.

Open preloaded workflow on RunComfy

Open preloaded workflow on RunComfy (browser)

Why RunComfy first
- Fewer missing-node surprises - run the graph in a managed environment before you mirror it locally.
- Quick GPU tryout - useful if your local VRAM or install time is the bottleneck.
- Matches the published JSON - the zip follows the same runnable workflow you can open on RunComfy.

When downloading for local ComfyUI makes sense - you want full control over models on disk, batch scripting, or offline runs.

How to use (local ComfyUI)
1. Load inputs (images/video/audio) in the marked loader nodes.
2. Set prompts, resolution, and seeds; start with a short test run.
3. Export from the Save / Write nodes shown in the graph.

Expectations - First run may pull large weights; cloud runs may require a free RunComfy account.

Overview

MiniMax H3 Singularity Reference To Video turns character, style, and scene images into coherent clips while keeping the main subject recognizable across frames. The workflow uses Singularity v1.3 for multi-reference conditioning, an 8-step base pass to establish composition and motion, a 1.5x latent upscale, and a 4-step refinement pass to recover fine texture and edge detail. Use it for fashion editorials, stage performances, sci-fi sequences, and animation shots where identity, wardrobe, and art direction need to remain visually consistent.

Important nodes:

• References and prompt setup

• Base generation pass

• Latent upscale

• Refinement pass

• Assembly and export

Notes

MiniMax H3 Singularity Reference To Video | ComfyUI - see RunComfy page for the latest node requirements.