🤖 Smolagent: Multi-Modal Agent with Hugging Face Space Discovery
Ask the agent to perform tasks...
Enter your prompt
Optional File Inputs
â–¼
Image Input
Drop Image Here
- or -
Click to Upload
Audio Input
Drop Audio Here
- or -
Click to Upload
Video Input
Drop Video Here
- or -
Click to Upload
3D Model Input
Drop File Here
- or -
Click to Upload
Generic File Input (PDF, TXT, etc.)
Drop File Here
- or -
Click to Upload
🚀 Generate
Outputs:
Image Output
Audio Output
3D Model Output
Text / Log Output
Download File Output
Output File Path
Example Prompts (Note: For examples with file inputs, you'll need to upload a relevant file first or ensure the named file exists in the Space's root)
Enter your prompt
Image Input