# Multimodal diffusion model
Cosmos Predict2 2B Video2World
Other
Cosmos-Predict2 is a high-performance pre-trained world foundation model designed for physical AI development, capable of generating physics-aware images, videos, and world states.
Text-to-Video
C
nvidia
314
8
Cosmos Predict2 14B Text2Image
Other
Cosmos-Predict2 is a series of high-performance pre-trained world foundation models designed for physical AI to generate physics-aware images, videos, and world states.
Text-to-Image
C
nvidia
312
15
Cosmos Predict2 2B Text2Image
Other
Cosmos-Predict2 is a series of high-performance pre-trained world foundation models designed to generate physics-aware images, videos, and world states, which can be used for the development of physics AI.
Text-to-Image
C
nvidia
473
19
Gligen Inpainting Text Image
Openrail
GLIGEN is a diffusion-based grounded text-to-image generation model capable of generating realistic images from text prompts, bounding boxes, and reference images.
Text-to-Image
G
anhnct
108
1
Featured Recommended AI Models