suvadityamuk/world-model-rl-trackio-bucket
63.5 MB
Suvaditya Mukherjee PRO
suvadityamuk
AI & ML interests
Computer Vision, Text-to-Image/3D Generation, Multimodal Models
Recent Activity
updated a bucket about 8 hours ago
suvadityamuk/world-model-rl-trackio-bucket updated a dataset about 9 hours ago
suvadityamuk/nasa-3d-resources updated a dataset about 16 hours ago
suvadityamuk/designgym-studio-assetsOrganizations
-
ComboStoc-XL/2 ImageNet 256
🎲Class-conditional ImageNet 256 (ComboStoc-XL/2)
-
Terrain Diffusion Infinite Panorama
🏔Infinite-width panorama generation with SD1.5
-
Colorful Noise
🎨1Training-free color-conditioned SDXL via FFT noise mixing
-
Inspiration Seeds
🌱1Fuse two images into diverse compositions, no prompt
A collection of some of the most used text-to-3D and image-to-3D models!
-
ComboStoc-XL/2 ImageNet 256
🎲Class-conditional ImageNet 256 (ComboStoc-XL/2)
-
Terrain Diffusion Infinite Panorama
🏔Infinite-width panorama generation with SD1.5
-
Colorful Noise
🎨1Training-free color-conditioned SDXL via FFT noise mixing
-
Inspiration Seeds
🌱1Fuse two images into diverse compositions, no prompt
spaces 35
Running
Agents
World Model Rl Trackio
🎯
Display real-time tracking data on a map
Running
17
World Models: The Simulation Strikes Back
🌍
The Simulation Strikes Back -- what even is a world model?
Running
World Lab
🌌
Explore action outcomes in a simple 2D world
Running
Matter Sampled — Geometry Lab
🫧
Explore a torus as points, mesh, or splats
Running
Motion from Noise
🎞
Explore video diffusion by revealing images from noise
Running on Zero
Agents
1
World Model Arena
🌐
Run a CPU‑only web service with FastAPI
models 32
suvadityamuk/Pixal3D-diffusers-3d
Image-to-3D • Updated • 14
suvadityamuk/sam-3d-objects-diffusers-3d
Image-to-3D • Updated • 16
suvadityamuk/Hunyuan3D-2.1-diffusers-3d
Image-to-3D • 3B • Updated • 17
suvadityamuk/Step1X-3D-Geometry-1300m-diffusers-3d
Image-to-3D • 1B • Updated • 16
suvadityamuk/TripoSG-diffusers-3d
Image-to-3D • 1B • Updated • 16
suvadityamuk/TRELLIS.2-4B-diffusers-3d
Image-to-3D • Updated • 49
suvadityamuk/TRELLIS-text-large-diffusers-3d
Text-to-3D • Updated • 61
suvadityamuk/TRELLIS-image-large-diffusers-3d
Image-to-3D • Updated • 53
suvadityamuk/Hunyuan3D-2.1-Paint-diffusers-3d
Image-to-3D • 2B • Updated • 11
suvadityamuk/Step1X-3D-Texture-diffusers-3d
Image-to-3D • 3B • Updated • 11
datasets 23
suvadityamuk/nasa-3d-resources
Viewer • Updated • 931 • 22 • 1
suvadityamuk/designgym-studio-starts
Viewer • Updated • 2.24k
suvadityamuk/designgym-studio-assets
Viewer • Updated • 3.13k
suvadityamuk/designgym-studio-transitions
Viewer • Updated • 124k
suvadityamuk/smithsonian-open-access-3d
Updated • 9 • 1
suvadityamuk/gso-footwear-trellis2-latents
Viewer • Updated • 9 • 697
suvadityamuk/gso-footwear
Updated • 72
suvadityamuk/world-model-arena-releases
Updated • 429
suvadityamuk/agentic-3d-worlds
Viewer • Updated • 4 • 211
suvadityamuk/ox-alpha-threejs-eval
Updated • 31