LTX 2.3 + LTX Director
https://youtu.be/_6w_S--2xB8

https://redd.it/1tr1xlg
@rStableDiffusion

Best local AI models for 16GB VRAM?
https://redd.it/1tr2ijg
@rStableDiffusion

Some Anima base generations

https://redd.it/1tr8xkx
@rStableDiffusion

Italy in the 1980s (Z-Image Turbo - Wan 2.2)

https://redd.it/1tr9539
@rStableDiffusion

Nava - A 6.3B audio-video model .

https://redd.it/1trb93v
@rStableDiffusion

Colored Noise Diffusion Sampling - plug-and-play, inference-time sampler.

https://redd.it/1tray25
@rStableDiffusion

Qwen Image Bench - Finetune for image eval
https://huggingface.co/Qwen/Qwen-Image-Bench

https://redd.it/1trgfmn
@rStableDiffusion

LTX 2.3 Character Dialogue

https://redd.it/1trkyr0
@rStableDiffusion

What would you run on an RTX Pro 6000 Blackwell?

Lots of people ask about what to run on small GPUs, but nobody asks about big GPUs. What would you do with 96GiB of VRAM?

I play with Z-Image and LTX (and derivatives like Sulphur), and I use Qwen for image editing. I still dabble a bit with older SD1.5 and SDXL models because there are so many useful loras, and they run fast so it's easy to generate a huge batch and then cherry-pick the best results.

Pic is the system with the Blackwell card and the old Ada card. Color-cycling RGB because my inner child is still alive and loves this BS. I'll do minimalism when I die.

https://preview.redd.it/lr0ji4tz964h1.jpg?width=4032&format=pjpg&auto=webp&s=8fc9962eaba7077e08425d0ab52b416a5fb8ee7a



https://redd.it/1trlcpu
@rStableDiffusion