REC Prompt-to-Video Playground
Open Source

Experiment with
AI Video

ComfyDirector is an open-source playground on top of ComfyUI. Give it a prompt, pick a workflow, and try ideas without learning node graphs, wiring models by hand, or living inside a giant workflow mess.

Cinematic 2.35:1 16:9 Widescreen 9:16 Vertical 4:5 Social
Featured Output

Cyber-Wasteland

Cinematic Lighting 24fps ComfyUI + LTX-2
Format Playground

Pick a frame. Compare the same idea.

Switch between cinematic, widescreen, portrait, and social crops to see how framing changes the result. It is a quick way to test composition before you commit to a workflow.

sample clips

Ratio
Focus
Feel
Garden Atmosphere 2.35:1
More room for atmosphere
Use this when the environment should carry real weight instead of just sitting behind the subject.
Featured Output 2.35:1
City and subject can coexist
The wide crop keeps the skyline readable without shrinking the action into the distance.
Character Scene 2.35:1
Good for slower scenes
Extra width helps a shot breathe when pacing matters more than speed.
Puppy Clip 16:9
Balanced and easy to read
16:9 is the easiest place to test an idea when you want subject, motion, and background to all stay clear.
City Experiment 16:9
A strong default frame
It is usually the safest starting point when you want quick comparisons without dramatic cropping.
Scene Texture 16:9
General-purpose widescreen
If you are not sure which frame to try first, this one usually gives the cleanest baseline.
Studio Portrait 9:16
Portrait puts the subject first
The tall crop cuts side noise and keeps the subject dominant.
Anime Alley 9:16
Vertical pushes focus forward
It reads fast on phones and makes faces or figures carry more of the shot.
City Crop Study 9:16
A fast reframing test
Useful when you want to see how a wide source behaves as a phone-first vertical.
Social Puppy 4:5
Compact without going full vertical
4:5 keeps the main subject large but still leaves some breathing room around it.
Studio Feed Cut 4:5
Good for feed-style previews
Useful when you want a social-friendly crop without committing all the way to 9:16.
Color Study 4:5
A practical social middle ground
It trims the edges, keeps the center strong, and lands between widescreen and portrait.
About

Why I Built This

ComfyDirector started as a way to mess with AI video without constantly wrestling with raw node graphs.

It wraps ComfyUI in a simpler layer so you can throw in a prompt, try different templates, and compare results without learning every workflow detail first. The point is not to hide the mess completely. The point is to make it easier to play with.

Workflow Experiments

A lighter way to mess around with prompts, templates, framing, and workflows without learning raw ComfyUI first.

Highlighted Feature

Frame choice changes the result.

The same prompt can look completely different at 2.35:1, 16:9, 9:16, or 4:5. ComfyDirector lets you compare those shapes early instead of treating aspect ratio like an afterthought.

Cinematic
16:9
9:16
4:5

LLM Prompt Expansion

Start with a rough idea and let the built-in LLM turn it into scenes, shot directions, and prompts you can actually test.

Visual Storyboard

See key images and scene beats before you commit to a heavier video run.

Cinematography Control

Try camera presets and shot variations without touching a raw ComfyUI graph.

Self-hosted & Cloud Ready

Run it on your own GPU or move the stack to cloud hardware when local VRAM is not enough. RunComfy support is there too, but still experimental.

Format Playground

Swap between cinematic, widescreen, portrait, and social framing to see how the same idea changes.

Asset Database

Your tests do not disappear into random output folders. Prompts, images, videos, and variants stay together.

Built-in Editor

Make a rough cut inside the app. Reorder clips, trim them, and stitch together something watchable without leaving the experiment.

How the Workflow Works

1

Prompt

Write the idea in plain English. No node graph needed.

2

Expand

AI turns it into scenes you can review, tweak, and approve before the heavy stuff runs.

3

Generate

Pick a template and let ComfyDirector run the matching ComfyUI workflow behind the scenes.

4

Assemble

Clips and audio can be stitched into a simple final video.

Built for messing around: rerun stages, swap templates, tweak prompts, change seeds, and keep going until something interesting shows up.

Available Workflows

8 Gen 2 templates across 5 GPU tiers — from lighter 8GB experiments to 32GB+ LTX 2.3 cinematic and lip-sync workflows.

8 GB RTX 4060, 3070

Quick Video

1 step

Fast text-to-video with Wan 2.2 5B. Sound design via MMAudio. Perfect for quick experiments on modest GPUs.

Prompt Video Sound
Sound Design
16 GB RTX 4080, A4000

Audio+Video

3 steps

Synchronized audio and video in a single pass with LTX-2. Camera control, face enhancement, and LoRA support built in.

Image Camera Video+Audio
Native Audio Camera LoRA Face Detailer
20 GB RTX 4070 Ti Super, A5000

Studio Video

1 step

Dual-expert MoE architecture delivers the highest quality text-to-video. LoRA support for style customization.

Prompt Video
LoRA Sound Design

Anime Studio

1 step

Specialized anime pipeline with curated LoRAs: retro 90s, modern HD, and Kawajiri styles. Built on the 14B MoE backbone.

Prompt Anime Video
LoRA Sound Design
24 GB RTX 4090, A5000 Ada

Cinematic Film

5 steps

The complete cinematic pipeline. Hybrid video (S2V lip-sync + LTX-2 motion), TTS narration, multi-character support, face enhancement, and opt-in image refinement before video.

Character Image Camera TTS Video
Hybrid Video TTS Camera LoRA Face Detailer Refinement Sound Design
32 GB+ RTX 5090, 32GB-class GPUs

Audio+Video 2.3

3 steps

Experimental LTX 2.3 native audio+video. Keeps the Qwen image and camera stages, then upgrades the final pass to newer synchronized dialogue and ambient audio generation.

Image Camera Video+Audio
Native Audio Dialogue Camera LoRA Experimental

LTX Cinematic

1 step

Direct LTX 2.3 text-to-video with synchronized audio. Best when you want the newest cinematic backend without the full multi-stage image and camera pipeline.

Prompt Video+Audio
Native Audio LoRA Refinement Experimental

LTX Cinematic Lip-Sync

3 steps

Audio-driven LTX 2.3 talking shots from one scene image plus uploaded or generated dialogue. Built for cinematic talking-head clips with storyboard image fallback.

Image TTS/Audio Lip-Sync
Audio Upload TTS Talking Head LoRA Experimental

Plus 6 legacy templates (Gen 1) still available for backward compatibility.

System Requirements

ComfyDirector runs locally if you have enough GPU headroom. The lighter templates start around 8GB VRAM, while the newest LTX 2.3 routes start at 32GB and the direct LTX Cinematic workflow is aimed at 48GB-class cards. Most of the hands-on testing so far has been on an RTX 5090.

If your machine is smaller, cloud GPUs are still a valid way to play with it. Some templates also support the RunComfy API, though that path is still experimental.

Read detailed Hardware Guide
GPU VRAM 8GB+ (32GB+ for LTX 2.3 experimental)
System RAM 32GB+ (64GB ideal for LTX 2.3)
Disk Space Variable (Depends on installed templates)
Platform Linux / WSL2

Support the Project

ComfyDirector is an open-source side project built in spare time. If it saves you from wrestling with raw ComfyUI just to test a prompt, Buy Me a Coffee helps cover the time and experiments behind it.

If you would rather not donate, starring the repo, opening issues, and contributing workflows or templates are still extremely useful signals.