#diffusion

JoyAI-Image-Edit-Plus is 24B — bigger than Qwen-Image-Edit. FP8 fits 16GB; BF16 needs 24GB. 5 GPUs ranked for local instruction edits in 2026.

Krea 2 RAW needs 24GB for LoRA training; Turbo 8-step runs on 12GB. 5 GPUs ranked from RTX 4060 Ti 16GB to 5090 for the new #1 T2I model.

A new paper introduces Vidu S1, a video model that generates interactive 540p video at up to 42 frames per second on consumer GPUs and lets users reshape the scene on the fly with voice commands, without the drift that usually breaks long AI video.

Diffusion text models generate in parallel blocks rather than left to right; Google's open DiffusionGemma and Inception's Mercury 2 are now in a head-to-head over speed.

iLLaDA is an 8-billion-parameter model that generates text by refining a blurry whole rather than one word at a time, and it's catching up to the mainstream.

A different style of text AI can go back and change any word at any point as it writes. Given that power, it didn't actually produce better writing. A clean negative result.

PhysiFormer forecasts physical motion as real 3D meshes in space - and recovers rigidity and momentum without anyone hand-coding the laws of physics.

A new recipe applies the same reinforcement-learning approach that polished chatbots to an image generator, then merges separate skill models into one - improving how faithfully it follows prompts and edits.

A new NVIDIA recipe distills slow video-generating AI into a fast version that can stream frames live and react to your actions.

Image-generating models often quietly break the very rule they were told to follow. A new method trains them to notice that error as they work and steer back on target.

MrFlow speeds up diffusion image models like FLUX by generating a rough image at low resolution, sharpening it with a fast GAN, and refining details at full resolution -- reaching roughly 10x end-to-end speedup with almost no quality loss and no retr

A new training-free method generates 3D visual illusions — one sculpture that reads as completely different objects depending on where you stand — in minutes instead of hours.