Wan 2.2, FLUX Krea & Qwen Image Upgraded: Fast 8-Step Presets Tutorial
Wan 2.2, Qwen Image, FLUX and FLUX Krea get new SwarmUI presets after a week of research, and new 8-step LoRAs make Wan 2.2 video and Qwen Image fast.

Highlights
Ultimate tutorial for these open source SOTA image and video gen models: 1-click install of SwarmUI with the ComfyUI backend, automatic preset import, the model downloader, RIFE frame interpolation and FLUX Krea DreamBooth and LoRA training results, on Windows, RunPod and Massed Compute.
Video tutorial
Wan 2.2 vs Wan 2.1: Same Prompt, Huge Difference in AI Video (8-Step Presets) · chapters and summary
More videos: Turn One Photo Into a Talking or Singing Video: MultiTalk Wan 2.1 Full Tutorial (1-Click), No Big GPU? Run ComfyUI and SwarmUI on a Rented 96GB Cloud GPU (RunPod RTX Pro 6000), ComfyUI Too Hard? Make AI Images and Videos Locally With SwarmUI (1-Click Install, 2025)
Related

SwarmUI Auto Installer & Ultimate Image and Video Model Downloader
SwarmUI auto installer with extensions plus a unified AI models downloader for SwarmUI, ComfyUI, Automatic1111 and Forge, with 105 ready SwarmUI presets.

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.

ComfyUI & SwarmUI on Massed Compute and RunPod: Cloud GPU Tutorial
ComfyUI and SwarmUI set up in 1 click on Massed Compute and RunPod cloud GPUs, with multi-GPU backends for faster Qwen, FLUX and Wan 2.2 generation.
More in SwarmUI: 1-Click Installer, Model Downloader and Tutorials.