stepfun-ai/Step-3.7-Flash
Image-Text-to-Text • 201B • Updated • 9.26k • 185
Eduardo Fonseca
ebfio
·
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
stepfun-ai/Step-3.7-Flash liked a model 1 day ago
stepfun-ai/Step-3.7-Flash-FP8 liked a model 18 days ago
nvidia/Kimi-K2.6-NVFP4Organizations
liked 2
models 1 day ago
liked a
model 18 days ago
liked a
model 26 days ago
liked 2
models about 1 month ago
SM120 support?
👀 1
1
#4 opened about 1 month ago
by ebfio
SM120 support?
👀 3
2
#2 opened about 1 month ago
by ebfio
liked 4
models about 1 month ago
MOE 122b and 397b please!
🚀 23
14
#7 opened about 1 month ago
by 
jesleocizi
liked 3
models about 1 month ago
reacted to imnotkitty's post with 👍😎🤗👀 about 2 months ago
Post
2617
Just tried 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."
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."