Models Directory

CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.

Create stickers from faces.

High quality zero-shot personalization

Vision

Generate videos from prompts using LTX Video

Generate videos from images using LTX Video

Multimodal vision-language model for video understanding

Anime finetune of Würstchen V3.

Stable Cascade: Image generation on a smaller & cheaper latent space.

Image based high quality Virtual Try-On

Large Language Models model. Pricing info:

Large Language Models model. Pricing info:

Our cutting-edge language model for coding with the first version released May 2024

Large Language Models model. Pricing info:

Large Language Models model. Pricing info:

Large Language Models model. Pricing info:

Large Language Models model. Pricing info: