Facepoke is so awesome! Haven’t had this much fun clicking around on photos since Kai‘s Power Goo. But unlike Kai‘s, Facepoke isn‘t just fun. It‘s actually very helpful for finetuning faces.

As a gamer, I am absolutely loving this! Managed to finish a level in Ms. Pac-Man. Hard to believe but the controls and game mechanics are working great. And it runs just as smooth on a M1 as it does on a 4090.

Major E2-F5-TTS Update! Now the 1-click launcher uses the OFFICIAL github repo (Originally it was using an unofficial fork). Notable updates: 1. Podcast generation (Mutli-voice) 2. Multiple speech type generation (Multi-emotion) 3. Improved batching 4. Audio crossfading

This is how I imagine the future with AR/VR

F5-TTS Finetune Web UI The E2-F5-TTS project has a huge update. Now anyone can easily finetune the model with their own audio using a Gradio app! It automatically transcribes the audio clips using whipser, and seems to work for most languages. Here's a Korean example.

Some tips on doing your own E2/F5 TTS finetune. Has anyone succeeded in training a working finetune yet? I've not been able to keep track of everything going on in the original training thread.

I’m very impressed by what you can do by combining F5 TTS with FaceFusion 3. Made a video about what I learned so far (using only F5 for the voiceover). youtube.com/watch?v=-brbxJ…

WOW, The Rock and Lex Fridman cloned using 100% local and open source AI tools. Completely for free. - F5-TTS for cloning voice - Facefusion for cloning face Check out the full video to learn how you can do it too on your computer.

Pyramid Flow over FLUX Pyramid flow is a video gen AI that's been around a bit, but the original version was bad (based on SD3). But they retrained the model using FLUX. Now it's REALLY good. Both txt2vid and img2vid. Even works on Macs! Gradio App 1-Click Launcher is here.

dont make plans for tomorrow

Custom Avatar with Echomimic 2 Wow I actually tried to do something like this with no success. I am guessing the trick here is to use a photo that has the same pose? Would appreciate if you could briefly explain how you did this! Mikerhinos

The Ultimate Tutorial for Mastering Voice Cloning with Fish Audio and E2-F5-TTS I can't believe this is just 8 minutes long but teaches everything you need to know about Fish and F5. Even for me, 90% of the content was new and I learned A LOT. A STRONG recommend!

Here’s a 100% free workflow for making your own AI influencers talk so that they can be used as virtual video presenters for example. youtu.be/-5fWC7RYXYk

1-Click HunyuanVideo ComfyUI Launcher This week we have tons of Pinokio updates coming up. Let's start the week with the best open source video AI we've ever seen: Hunyuan Video. A 1 Click launcher for ComfyUI-HunyuanVideoWrapper by Jukka Seppänen - run locally, for free.

THE BELOW VIDEOS ARE 100% AI-GENERATED WITH AN OPEN-SOURCE MODEL, A COMPETITOR TO SORA! Marques Brownlee You can generate videos with it using a consumer-level GPU right now. Contact me, and I will provide you with a user interface and free unlimited generation to try open-source models.

💃 StableAnimator: High-Quality Identity-Preserving Human Image Animation 🕺 template with @gradio 🥳 Thanks to Shuyuan Tu ❤ Zhen Xing ❤ Xintong Han ❤ Zhi-Qi Cheng ❤ Qi Dai ❤ Chong Luo ❤ Zuxuan Wu ❤ 🌐page: francis-rings.github.io/StableAnimator/ 🧬code: