Proof-of-concept image generator from Unconventional AI that uses coupled oscillators instead of diffusion.
Updated EU status checked Last shown
Sources: creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Un-0 is an experimental image generation model from Unconventional AI. According to a creator review, it generates images with coupled oscillators rather than the diffusion approach used by most current image models.
It is described as a proof of concept. Reported output quality is poor, so it is a demonstration of an alternative computing and generation approach rather than a competitive image generator.
Weights and training scripts are reportedly released under the MIT license. No official page could be fetched, so release date, hosting location and other details are unverified.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Image generator using coupled oscillators instead of diffusion. Image quality is poor and it's a proof of concept; weights and training scripts are open-source under MIT.
Closest neighbours by meaning, not just by category.
Research
Proof-of-concept image generator that learns an energy function and lowers it iteratively instead of denoising.
Model
Diffusion model from Speridlabs that turns a single image into a 3D Gaussian splat object at adjustable detail levels.
Model
One- and two-step image generation model distilled from Z-Image-Turbo using text-stream adversarial distillation.
Research · ByteDance
ByteDance and Texas A&M research method distilling image and video diffusion models into few-step generators adversarially.
Model
Open-weights 6B text-to-image model family from Alibaba's Tongyi-MAI lab, with a fast 8-step Turbo variant.
Model · inclusionAI
Open-weights 6B unified text-to-image and instruction-based image editing model family from inclusionAI.