ComfyUI workflow pack · 18+

Image + Video Pack: stills + clips, consistent across both without censorship, on your own GPU

Both pipelines in one bundle: renders a high-resolution image, then animates it into a clip with sound while character and setting stay identical. $89 one-time. The pack runs entirely on your hardware, a local NVIDIA GPU or a rented RunPod instance, so prompts and output never pass through our servers and no age-verification database is involved.

EverythingImage + Video Pack$89 once

Everything from the standalone packs, combined into one pipeline. Write a scene and it renders as a high-resolution image, then animates into a clip with sound while the character and setting stay identical across both. Editing is built in too: restyle or swap a person in any image and their identity stays intact.

The workflow

What you get

• Both image and video workflows
• Identity-preserving photo editing
• Motion-synced audio included
• Runs on 32 GB+ GPUs
• 90 GB disk for models
• One-click Docker setup for both
• Local or RunPod

Requirements

NVIDIA GPU with 32 GB+ VRAM (RTX 5090 locally, or RunPod 5090 / RTX 5000 Ada / A6000+)

Docker with the NVIDIA Container Toolkit, or a RunPod account for cloud GPUs

Persistent storage for model files: 30 GB (Image Pack), 60 GB (Video Pack), or 90 GB (Image + Video Pack).

How it works

1Complete your purchase; your license key appears here instantly.

2Log in to the registry with your key and pull the Docker image; models download on first startup.

3Open the ComfyUI interface on port 8188 and start generating.

Setup guides

Local setup guideRunPod setup guideGPU requirements

Which models does the Image + Video Pack run on?

Krea-2, MiniMax-H3, Qwen3-VL, plus the tuned LoRAs and pre-calibrated settings that ship inside the pack. Everything installs with one command; nothing to wire up, everything stays adjustable.

Last verified October 2026. Adults only (18+). All sample output is synthetic, computer-generated fiction.