VideoWorld 2: Learning Transferable Knowledge from Real-world Videos Paper • 2602.10102 • Published 6 days ago • 14
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions Paper • 2403.19651 • Published Mar 28, 2024 • 26
view post Post 5051 We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe See translation 1 reply · 🔥 29 29 🤗 5 5 + Reply
Paused Featured 94 FLUX.1 Dev ControlNet Union Pro 2.0 🔥 94 Generate images using prompts and control images
Running on Zero Featured 1.75k Dia 1.6B 👯 1.75k Generate realistic dialogue from a script, using Dia!
Sleeping 1 Audio To Image And Text Gen Model 🖼 1 A Multimodal Application for Vernacular Language Translation
OmniSVG: A Unified Scalable Vector Graphics Generation Model Paper • 2504.06263 • Published Apr 8, 2025 • 182