Generate video from text and images using NVIDIA's 2B Cosmos Post-Trained Model

fal-ai/cosmos-predict-2.5/image-to-video

Generate video from text and images using NVIDIA's 2B Cosmos Post-Trained Model

Inference

Commercial use

Schema

LLMs

Playground API

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

fal-ai/cosmos-predict-2.5/image-to-video

Schema

LLMs

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Input

Prompt*

A static, locked-off camera frames an industrial conveyor belt steadily transporting rough rocks through a dimly lit quarry processing facility. The belt runs horizontally across the center of the frame, its thick black rubber surface textured with dust and fine gravel. Jagged gray and brown stones of varying sizes tumble forward in a slow, continuous motion, their sharp edges catching the light. Subtle vibrations ripple through the belt’s surface as small pebbles bounce and shift. In the background, blurred steel beams, pipes, and muted industrial machinery create depth without distraction. Cool, diffused overhead lighting casts soft shadows and highlights the gritty textures, emphasizing dust particles in the air and the raw, rugged surfaces of the rocks.

Type # to reference inputs.

Image URL*

Hint: Drag and drop image files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: jpg, jpeg, png, webp, gif, avif, heic, heif

Additional Settings

Customize your input with more control.

Your request will cost $0.20 per video. Videos have a fixed size of 1280x704 and a fixed duration of 93 frames at 16 frames per second (5.8 seconds.)

Result

Idle

This generation takes approximately 7m.

What would you like to do next?

Download

Your request will cost $0.20 per video. Videos have a fixed size of 1280x704 and a fixed duration of 93 frames at 16 frames per second (5.8 seconds.)

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Input

Prompt*

Type # to reference inputs.

Image URL*

Hint: Drag and drop image files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: jpg, jpeg, png, webp, gif, avif, heic, heif

Additional Settings

Customize your input with more control.

Your request will cost $0.20 per video. Videos have a fixed size of 1280x704 and a fixed duration of 93 frames at 16 frames per second (5.8 seconds.)

Result

Idle

This generation takes approximately 7m.

What would you like to do next?

Download

Your request will cost $0.20 per video. Videos have a fixed size of 1280x704 and a fixed duration of 93 frames at 16 frames per second (5.8 seconds.)

Cosmos Predict 2.5 2B (Image to Video) API on fal