Cosmos3-Nano
NVIDIA Cosmos3-Nano — text/image to video + audio
NVIDIA Cosmos3-Nano — text/image to video + audio
State-of-the-art image generation, in your browser.
Segment objects in live webcam and uploaded media
Operators over the three Epicure ingredient embeddings
Training-free reference-guided generation with FLUX.2-klein
Dense video captions and timestamp search
Generate full HTML web apps from text prompts
Chat with an AI assistant using the LFM2.5 model
📷Torch 📚Transformers 🖼️CV 🧠SFT
📷Torch 📚Transformers 🖼️CV 🧠SFT
Extract research metadata from URLs
Food image classification
Image classification model which classifies upto 120 breeds
Find similar research papers using semantic search
Detect coughs and get health analysis
Detect and classify Windows malware from executable files
Compute image‑text similarity with CLIP and view results