SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model. Separation (sep-12k) and generation (gen-3k) checkpoints.
Aviad Dahan
AviadDahan
AI & ML interests
Deep Learning Researcher @ Tel Aviv University
Recent Activity
published a dataset 2 days ago
AviadDahan/SepGen-Dataset updated a dataset 2 days ago
AviadDahan/SepGen-Dataset published a model 2 days ago
AviadDahan/SepGen-GenerationOrganizations
None yet
models 8
AviadDahan/SepGen-Generation
Text-to-Video • Updated • 19
AviadDahan/SepGen-Separation
Audio-to-Audio • Updated • 18
AviadDahan/LTX-2.3-ID-LoRA-TalkVid-3K
Any-to-Any • Updated • 1.81k • 62
AviadDahan/LTX-2.3-ID-LoRA-CelebVHQ-3K
Any-to-Any • Updated • 1.81k • 66
AviadDahan/ID-LoRA-CelebVHQ
Any-to-Any • Updated • 406 • 8
AviadDahan/ID-LoRA-TalkVid
Any-to-Any • Updated • 392 • 8
AviadDahan/Meta-Llama-3-8B-fp16-gguf
Text Generation • 8B • Updated • 46 • 5
AviadDahan/Meta-Llama-3-8B-Instruct-fp16-gguf
Text Generation • 8B • Updated • 22 • 3