Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
Paper • 2305.10973 • Published • 39 •
74
Zero Collabs
ZeroCollabs
AI & ML interests
None yet
Recent Activity
reacted to imnotkitty's post with 🔥 about 2 hours ago
Just tried https://huggingface.co/tencent/HY-World-2.0 — a multimodal world model that takes in text or a single image and generates editable 3D scenes.
Unlike Google's Genie and HY-World 1.5, v2.0 generates engine-ready 3D content:
🎮 Direct import into Unreal Engine and Unity — no format wrangling
🧊 Supports multiple 3D asset formats: Mesh, 3DGS, point cloud, etc.
✏️ Fully editable — not a baked video, but actual geometry you can modify
🤖 Also usable for embodied simulation environments
Basically: from "AI generates a world you can look at" → "AI generates a world you can ship." liked a model 2 days ago
Jiunsong/supergemma4-26b-uncensored-gguf-v2 liked a Space 2 days ago
linoyts/LTX-2-3-syncOrganizations
None yet
commented a
paper almost 3 years ago