BudgetPix: Compute-Adaptive Tokenization for Pixel-Space Image Diffusion
BudgetPix adapts image-diffusion token budgets to visual complexity, matching larger models at a fraction of compute.
Stories per day · 30 days
1 RSS
Relatedimage-generation3budgetpix1compute-efficiency1depth-estimation1diffusion1encoder-free1fid1huggingface1iris-3b1mixture-of-transformers1multimodal1open-weights1qwen1tokenization1video-generation1vision1
3 stories, newest first · one card per story
Stories tagged #pixel-space
speridlabs/iris-3b — new model trending #30 on Hugging Face
Sperid Labs released Iris-3B, a 3-billion-parameter pixel-space image model that also does depth and upscaling.
3
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation
PixelUMM unifies encoder-free image and video understanding and generation in raw pixel space.