VideoWorld 2: Learning Transferable Knowledge from Real-world Videos Paper β’ 2602.10102 β’ Published 5 days ago β’ 14
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions Paper β’ 2403.19651 β’ Published Mar 28, 2024 β’ 26
view post Post 4965 We collaborated with Hugging Face to enable you to train MoE models 12Γ faster with 35% less VRAM via our new Triton kernels (no accuracy loss). π€Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe See translation 1 reply Β· π₯ 29 29 π€ 5 5 + Reply
Paused Featured 94 FLUX.1 Dev ControlNet Union Pro 2.0 π₯ 94 Generate images using prompts and control images
Running on Zero Featured 1.75k Dia 1.6B π― 1.75k Generate realistic dialogue from a script, using Dia!
Running 1 Audio To Image And Text Gen Model πΌ 1 A Multimodal Application for Vernacular Language Translation
OmniSVG: A Unified Scalable Vector Graphics Generation Model Paper β’ 2504.06263 β’ Published Apr 8, 2025 β’ 182