Zenith

Following the latest AI tech and what it offers, and supporting great community and real-world utility crypto projects. Let's Go!

[Zenith @FlamingZenith]

@truthpole Hmm....Could be a benevolently disguised alien takeover for transhuman integration of Earth population. Will they arrive with fancy enticing tech that requires some sort of agreement or covert invasive changes to the body? Who knows

[A.I.Warper @AIWarper]

Viggle AI launched their real time video today!

Tested it and it's pretty great.

Another first to market (that I am aware of for them)?

Link below 👇

[ViggleAI @ViggleAI]

Pretty sure we're the first to market 😎

[Alex Patrascu @maxescu]

Veo 3 is generations ahead of everyone else.

The script has been flipped:

[Krea @krea_ai]

introducing Krea Lipsync.

this new tool lets you create hyper-realistic talking videos of any character using @hedra_labs' new model.

try it now!

[MayorkingAI @MayorKingAI]

Create claymation stop-motion style images with ChatGPT

I started crafting a claymation-style prompt with ChatGPT…
and ended up improvising a Short AI film "After the Last Embrace"

Images: ChatGPT
Video: Kling 2.0 Master
SFX: Freepik
Music: Udio

Here's how🧵👇

[Zenith @FlamingZenith]

@VelvetVoiceWS Dude fell back on that sharp metal corner. He was in real pain.

[The AI Colony @TheAIColony]

🚨BREAKING: The world's first agentic browser just launched and it’s INSANE!

This AI browser doesn’t just help you browse, it does the browsing for you.

SPOILER: Googe chrome is now behind.

Here’s how it works:

[el.cine @EHuanglu]

wow.. ComfyUI's node canvas is crazy

we can now generate image, video, audio, even 3D models locally on the AI canva and..

it has all the top AI models like FLUX, GPT image, Kling, Veo, Hunyuan3D and more

step by step tutorial:

[Arsenii Turgulainen @ars3d]

Mixamo + realtime puppeteering in #UnrealEngine

[Science girl @sciencegirl]

"Twisted Chrysanthemum Joint," woodworking technique that interlocks wood pieces without nails or glue,

[MrNeRF @janusch_patas]

I am blown away 🤯. Check this out!

CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models

TL;DR:
"To enable broader exploration of dynamic scenes, our model can generate new video clips of the same scene based on previously generated content and user-provided camera trajectories. This approach maintains dynamic capabilities, accurate camera control, and scene consistency throughout the extended exploration."

"Our model enables precise camera control across diverse scenarios while preserving dynamic scene elements, e.g."

"Our method can generate videos with strong 3D consistency, which enables high-quality 3D reconstruction using the camera-controlled videos."

Contributions:
1) A systematic data curation pipeline for constructing a dynamic video dataset with camera trajectory annotations;

2) A lightweight camera control injection module and corresponding training strategy that preserves dynamic video generation capabilities while adding camera control effect;

3) A clip-wise autoregressive generation recipe that enables extended range exploration of generated scenes.

[Vidu AI @ViduAI_official]

🔥 New Vidu Update 🔥Multi-Reference Consistency
Now you can define a reference subject each with up to 3 images and @ mention it anytime for consistent video generation! 🎥
More stability, more references (up to 7!), and even better anime-style precision.
https://t.co/UI0p48sLv8

[AK @_akhaliq]

DeepMesh is out on Hugging Face

Auto-Regressive Artist-mesh Creation with Reinforcement Learning

Conditioned on point clouds and images, DeepMesh generates meshes with intricate details and precise topology, outperforming state-of-the-art methods in both precision and quality.

[ComfyUI @ComfyUI]

We are happy to announce that ComfyUI now natively supports @TXhunyuan  Hunyuan3D 2.0 and Hunyuan3D 2.0 MV (Multi-View) model series!

3 workflows to get started:

🔹Hunyuan3D-2 mv: multi-view to 3D
🔹Hunyuan3D-2 mv Turbo: accelerated multi-view
🔹Hunyuan3D-2: single image to 3D

[Gradio @Gradio]

KDTalker is really wild 🤯👇

- Can run on single 4090 or 3090 🤩
- Uses Diffusion for generating audio-driven Talking Portraits
- Preserves character identity with fine facial details
- Expressions change with the speech, giving high pose diversity

[AshutoshShrivastava @ai_for_success]

Wan 2.1 is the best open-source AI video model right now and probably the least censored as well and it a solid alternative to Google Veo-2.

How to use Wan 2.1 on ChatLLM in 30 seconds.

[Yuval Alaluf @yuvalalaluf]

Reality is just a rough draft.

Check out a sneak peek of our new feature @pika_labs!

[AK @_akhaliq]

ByteDance just announced InfiniteYou available on Hugging Face

Flexible Photo Recrafting While Preserving Your Identity

[an303042 @an303042]

I really had a lot of fun with @pika_labs (still unreleased) new feature!
Kids went NUTS for it! 🤯
Sound on! 🔊