Sleeping
MCP
FIRE3D Scene Reconstruction
🔥
Feed-forward 3D scene reconstruction from a single image
Hugging Apps
Team
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Running on Zero
Agents
1
Natural Face & Speech H3 LoRA
🗣
Talking-head video with natural face & speech motion
Running on Zero
Agents
Wushu Action LoRA · MiniMax-H3
🥋
Martial-arts action video+audio with MiniMax-H3
Running on Zero
MCP
1
MiniMax-H3 Video Sharpening LoRA
🔍
Sharpen a video with the MiniMax-H3 LMS detail LoRA
Running on Zero
Agents
2
MiniMax-H3 LMS Sharpen
🔎
Re-render a clip sharper with MiniMax-H3's LMS LoRA
Running on Zero
MCP
2
OracleZoom Super Resolution
🔎
Recursive 4x zoom to 256x with OracleZoom
Running on Zero
Agents
1
Insta / TikTok Aesthetics · MiniMax-H3 LoRA
📱
Vertical social-video style LoRA for MiniMax-H3
Running on Zero
Agents
MiniMax-H3 VR180 Stereo LoRA
🥽
Text to headset-ready VR180 3D video with audio
Running on Zero
Agents
Better Human Motion · MiniMax-H3 LoRA
🏃
Human-motion LoRA on MiniMax-H3 — video + stereo audio
Running on Zero
MCP
TeleOCR
📄
Parse digital & photographed documents into Markdown
Running on Zero
MCP
Xiaomi Robotics U0 4B
🤖
Autoregressive text-to-image and image editing
Running on Zero
Agents
Eyes Direction LoRA - FLUX.2 klein 9B
👀
Drag the googly eyes to redirect where the eyes look
Running on Zero
MCP
SyncWorld Simulator
🦾
Visually-calibrated zero-shot robot world simulator
Running on Zero
MCP
SAGA Micro-Drama VLM
🎬
Structure-aware micro-drama video understanding (SAGA)
Running on Zero
Agents
SpatialBlock
🧱
Spatial intelligence in LVLMs via synthetic block-stacking
Running on Zero
MCP
Werea-TR-TextRestore
✍
Restore Turkish diacritics in ASCII-ized text
Running on Zero
MCP
Bar-JEPA — Bar Chart Value Extraction
📊
Recover numeric values from bar chart images
Running on Zero
MCP
EXAONE Tabular
📊
In-context tabular prediction from a CSV
Running on Zero
MCP
LingBot-World-V2 1.3B
🌍
Camera-controlled image-to-video world model (1.3B)
Running on Zero
MCP
Echo-WM Flash
🌍
Camera-controllable world model with synced audio
Running on Zero
MCP
CVRR Visual Reasoning
🔁
Latent visual recurrent reasoning VQA on Qwen2.5-VL-7B
Running on Zero
MCP
1
Audio8 TTS Preview 0.1B
🗣
Zero-shot voice cloning TTS in ~170M parameters
Running on Zero
MCP
LLaDA-UI
🖱
GUI grounding & agent with a block-diffusion VLM
Running on Zero
MCP
1
PhysBrain 1.5-2B
🧠
Embodied spatial reasoning, grounding & pointing VLM