Heinrich Lab

i'm just a figment of your imagination

[NVIDIA AI @NVIDIAAI]

One image + text + camera trajectory = controllable worlds. All on a single GPU.

Our research team just released SANA-WM, a 2.6B open source world model natively trained for 60-second video generation with precise camera control.

[Heinrich Lab @GeekDynamics]

Do you remember when you joined X? I do! #MyXAnniversary

[Tencent Hy @TencentHunyuan]

Very cool to see Tencent HY 3D in Cinema 4D @MaxonVFX. Excited to see what people create with it🤓

[Tencent Hy @TencentHunyuan]

🚀 Tencent Hunyuan Image 2.0 Is Live!

Redefining real-time AI image generation with cinematic aesthetics and instant creativity.

⚡️ Highlights:
✅ Real-Time Text-to-Image: First commercial model with millisecond-level responsiveness, 15x faster than industry benchmarks — generate images as you type/speak.
✅ Hyper-Realistic Textures: Eliminates the 'AIGC look' through Slow-Thinking Reward Functions and Structured Rewriting Model — deliver cinematic textures and lighting.
✅ Dual-Canvas Studio: Sync ideas across canvases with AI-powered perspective/lighting coordination + multi-layer blending — unlock boundless creativity.

👉 Try It Now: https://t.co/U3966JuQHi
Sign in with your email to begin creating!
#TencentHunyuan #AI

[NVIDIA GeForce @NVIDIAGeForce]

Stand and Fight for a chance to win.

We're giving away a #DOOM: The Dark Ages custom wrapped NVIDIA GeForce RTX 5090 to celebrate its official release with native ray tracing, NVIDIA DLSS 4 + Reflex.

To enter:

🟢 Like this post
🟢 Comment #RTXON

[Heinrich Lab @GeekDynamics]

@NVIDIAGeForce Only a few have played the original doom since the autoexec.bat times, I'm one of them #RTXON

[Tencent Hy @TencentHunyuan]

Join us LIVE for the release of HunyuanImage 2.0!
https://t.co/Cl1EQq0JLW

[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

[Tencent Hy @TencentHunyuan]

We have deployed the accelerated models and inference code across all repositories. For instance, Hunyuan3D-2mv Turbo is now accessible in the Hunyuan3D-2mv repository here: https://t.co/YCGsNiMea1. If you find our models valuable, don’t forget to give it a star! 🌟

[Heinrich Lab @GeekDynamics]

@AllaAisling ok

[Tencent Hy @TencentHunyuan]

We are thrilled to announce a ​30x acceleration in white model generation speed across the entire Hunyuan3D 2.0 family, reducing the processing time from 30 seconds to just ​1 second.

[Hedra @hedra_labs]

Our new Character-3 model makes it easy to generate expressive animated characters with natural movement.

Just upload an image, add audio, and bring your scenes to life.

[Heinrich Lab @GeekDynamics]

@AllaAisling

[Mickmumpitz @mickmumpitz]

We wanted full control for our new AI movie “Paper Jam”, so we hand-animated all poses in an AI-generated 3D space.

Scenes were then rendered using @bfl_ml Flux with regional custom character LoRAs for consistency and interpolated with @Kling_ai

Tutorial + free workflows👇

[ComfyUI @ComfyUI]

Hunyuan @TXhunyuan Image2Video just dropped! Day-1 Native support is now available in all versions of ComfyUI (git/portable/desktop) 🔥🔥

This 13B model maintains the success in amazing quality, bringing another big moment for the open source community!

Check out how to get started in ComfyUI!

[Tencent Hy @TencentHunyuan]

HunyuanVideo I2V is here! 🚀🚀🚀🚀🚀🚀

I2V training code is here! 🛩️🛩️🛩️🛩️🛩️🛩️

Always Open Source & Open Cccess！

Github: https://t.co/0CUbPgR4ie

HuggingFace: https://t.co/8BaMmSQqTM

[Heinrich Lab @GeekDynamics]

@AllaAisling ok

[ComfyUI @ComfyUI]

3D == Matrix Multiplication == AI

Example of using WAN2.1 Image to Video in ComfyUI

[Heinrich Lab @GeekDynamics]

@AllaAisling Thinking bout something like Dali, but... this is glamorous

[Heinrich Lab @GeekDynamics]

@AllaAisling Surreal