Wan 2.1 T2V & I2V in SwarmUI Tutorial: CausVid LoRA for Extreme Speed
Wan 2.1 text-to-video and image-to-video in SwarmUI with the CausVid LoRA at just 8 steps; on an RTX 5090 a clip took 90 seconds versus 170 on an RTX 3090 Ti.

Highlights
Uses ComfyUI as the SwarmUI backend with Sage Attention, ready T2V and I2V presets, RIFE frame interpolation and GGUF models for low VRAM. Includes the SwarmUI installer and model downloader and the 1-click ComfyUI installer.
Video tutorial
Set Up Windows 11 for AI Apps: Python, CUDA, cuDNN, C++ Build Tools, FFmpeg and Git (2024 Guide) · chapters and summary
More videos: Image to Video in Under a Minute on an RTX 5090: Wan 2.1 + CausVid LoRA in SwarmUI (2025), ComfyUI Too Hard? Make AI Images and Videos Locally With SwarmUI (1-Click Install, 2025)
Related

Higgsfield Genjutsu Character Replace Locally: ComfyUI & SwarmUI
MiniMax H3 Genjutsu presets replace the person in any video with your own character from one image, keeping the clip's motion, camera and original sound.

Wan 2.2 & FLUX Krea Full Tutorial: 1-Click Install & SwarmUI Presets
Wan 2.2 and FLUX Krea Dev in SwarmUI with a ComfyUI backend, using ready presets built from hundreds of parameter tests for videos from text or images.

FramePack 1-Click Installers: Image-to-Video on Just 6 GB VRAM
FramePack, lllyasviel's image-to-video model, makes 30 FPS videos up to 120 seconds long in an advanced Gradio app with Sage Attention and Teacache support.