Stable Video Infinity v2.0 Pro installation tutorial. Consistent long AI videos. Free & uncensored #ai #aitools #aivideo

Thanks to our sponsor Genspark. Sign up today and get free credits, plus unlimited AI chat and image generation with Pro. https://www.genspark.ai/?utm_source=yt&utm_campaign=theAIsearch
Jan 1–7 only: Get 40% off any Annual plan—save $100 on Plus Annual or $1,000 on Pro Annual. @genspark_ai⁩  

Sources in order of mention
SVI main page: https://github.com/vita-epfl/Stable-Video-Infinity
ComfyUI tutorial: https://youtu.be/g74Cq9Ip2ik
KJnodes: https://github.com/kijai/ComfyUI-KJNodes
SVI 2 Pro workflow: https://github.com/user-attachments/files/24359648/wan22_SVI_Pro_native_example_KJ.json
Wan fp8 models: https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main/I2V
Lightx2v models: https://huggingface.co/lightx2v/Wan2.2-Distill-Loras/tree/main
SVI 2.0 Pro models: https://huggingface.co/Kijai/WanVideo_comfy/tree/main/LoRAs/Stable-Video-Infinity/v2.0
CLIP: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/text_encoders
VAE: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/vae
GGUFs https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/tree/main

0:00 SVI 2.0 Pro intro
0:33 Demos and strengths
3:42 Install KJNodes 
5:27 SVI 2 Pro workflow
6:40 Downloading all the models
11:24 Genspark
13:16 How to use SVI 2.0 Pro
17:34 Common errors
19:23 How to add loras
21:17 GGUFs for low vram

Newsletter: https://aisearch.substack.com/
Find AI tools & jobs: https://ai-search.io/
Support: https://ko-fi.com/aisearch

Here's my equipment, in case you're wondering:
Lenovo Thinkbook: https://amzn.to/4jWeKwH
Dell Precision 5690: https://www.dell.com/en-us/dt/ai-technologies/index.htm?utm_source=AISearchTools&utm_medium=youtube&utm_campaign=precisionai#tab0=0 
GPU: Nvidia RTX 5000 Ada https://nvda.ws/3zfqGqS
Mic: Shure SM7B https://amzn.to/3DErjt1
Audio interface: Scarlett Solo https://amzn.to/3qELMeu

YouTube

Stable Video Infinity version 2 Pro enables generation of long, consistent AI videos by chaining multiple 4-5 second clips from Alibaba's Wan 2.2 model. The tool is free, open-source, runs locally with as low as 6GB VRAM, and produces seamless transitions between clips while maintaining visual consistency. Installation involves setting up ComfyUI, downloading multiple model variants (high/low noise versions), and configuring a workflow with optional LoRA support for customization.

Long continuous AI video is here! Free & open-source