GitHub - YingqingHe/ScaleCrafter: Official implementation of ScaleCrafter for higher-resolution visual generation at inference time.
its called InvSR and is a diffusion based upscale method which only requires one to five steps
code: https://t.co/kLy3zg52QI
demo:... See more
Dreaming Tulpa 🥓👑x.com
Google presents Greedy Growing Enables High-Resolution Pixel-Based Diffusion Models
Propose a novel recipe for training non-cascaded large scale pixel-space text-to-image diffusion models
https://t.co/L4ElMddJoe... See more
Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection
"We propose Reflect-DiT, a method that enables
Diffusion Transformers to refine their generations using in-context examples of previously generated images alongside
textual feedback describing necessary improvements"__... See more