Incredibly, compared with DALL-E 2 and Imagen, the Stable Diffusion model is a lot smaller. While DALL-E 2 has around 3.5 Billion parameters, and Imagen has 4.6 Billion, the first Stable Diffusion ...
July 19th, 2023 at 04:29 pm
Stable Diffusion model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts. With its 860M UNet and 123M text encoder, the model is relatively lightweight and can run on ...
July 19th, 2023 at 12:38 pm
For example, using Stable Diffusion v1-5 with a ControlNet checkpoint require roughly 700 million(7亿) more parameters compared to just using the original Stable Diffusion model, which makes Control...
July 19th, 2023 at 10:36 am