Stable Cascade best new resource

Easily cranking out high quality 1536 x 1280 images in under 3 seconds using under 8gb Vram

https://github.com/Stability-AI/StableCascade

Stable Cascade consists of three models: Stage A, Stage B and Stage C, representing a cascade for generating images, hence the name "Stable Cascade". Stage A & B are used to compress images, similarly to what the job of the VAE is in Stable Diffusion. However, as mentioned before, with this setup a much higher compression of images can be achieved. Furthermore, Stage C is responsible for generating the small 24 x 24 latents given a text prompt. The following picture shows this visually. Note that Stage A is a VAE and both Stage B & C are diffusion models.

The attached picture is is far from my best I just thought it would be a good choice to show of the versatility. It was created with prompt: portrait photo of (taylor swift) wearing Kansas City Chiefs jersey #13, white background. No negative prompt, no lora, no embedding. You can get really good images in a really short time without having to tweak your settings.

The bad: you can barely tweak your settings, civitai can not parse the images for prompts. Difficult to use previously saved prompts.