PrismML just released Binary and Ternary Bonsai Image 4B: 1-bit/ternary text-to-image diffusion transformers that can even run 100% locally in your browser on WebGPU.
PrismML has released new text-to-image diffusion transformer models, Binary and Ternary Bonsai Image 4B. These models are significantly smaller than previous versions, with a size of approximately 3GB, and can run locally in a web browser using WebGPU. The models are released under the Apache-2.0 license. AI
IMPACT Enables more accessible, local execution of advanced image generation models.