We have retrained the UniAnimate model based on Wan2.1-14B-I2V recently. And we've released the report and open-sourced the training, inference code, and the models. You're welcome to try it out. Github: github.com/ali-vilab/UniA… Report: arxiv.org/pdf/2504.11289

Open Source NotebookLM Alternative on Your PC Wow Dia is REALLY good. 1. Voice clone 2. Non-verbal generation: (laughs), (coughs), .. 3. Dialogues: Just upload 1 clip with 2 voices to generate a NotebookLM style dialogue 1-Click Gradio Launcher. Mac, Windows, Linux.

This is amazing

Run all the local models you want, run all the closed models you want. No more choosing.

Tear up the dancefloor. Ex Machina style transfer in wan 2.1 1.3b

I spent the past months building OpenMuse.ai. Growing from the Banodoco community, my hope is that it’ll become a place people find extremely inspiring/empowering: a worthy home for the open source AI art movement🌱 Beautiful example of an LTXV LoRA by Mohamed Oumoumad:

Meanwhile in the open-source end of the pool, here's Wan + VACE + a style frame in ComfyUI 🤘 #aivideo Process images in thread 🧵

Excited for this session! Flipping Sigmas will be talking about how Wan is used for his professional workflow.

it's almost getting to where it's easier to get Claude or Gemini to code a ComfyUI node for you than searching for one

Marey Realism 1.5 by Moonvalley is now live in ComfyUI API nodes! First video model trained only on 100% licensed 1080P footages — pro quality, production-ready, and commercially safe. Now available: 🔹 Text-to-Video 🔹 Image-to-Video 🕙 Pose and Motion Transfer nodes coming

Messing with Wan and ComfyUI Purz.ai Machine Delusions Julien | MJM

Early tests with Pose Control and LipSync using free and open source tools that anyone can download and use at home if you have the will and a decent gpu. Wan

Using Moonvalley Marey model along with some other tricks to bring to life this poem I wrote and then made into song using Suno