alkinun

AtAndDev

·

https://baretile.com/

alkinun

AI & ML interests

decentralize

Recent Activity

reacted to savoji's post with 🔥 about 2 hours ago

Idol, a new Apache-2.0 image-to-3D model from @speridlabs, makes a 3D Gaussian splat from one image in 7.2 GB of peak VRAM. It is the #1 trending model on the Hub with 1,057 likes. It writes a standard 3DGS .ply with up to 1,048,576 Gaussians, including sides the picture never showed, and does background removal and framing itself. The catch: the only quality evidence is the authors' own benchmark, on a repo created 2026-10-28. 📊 The numbers • Authors' benchmark, 1 x H100: best in 6 of 8 columns vs TripoSplat, TRELLIS and LGM (SSIM 0.726, LPIPS 0.213, DINOv2 0.781, CLIP 0.885) • LGM wins PSNR (12.46 vs 12.25) and speed (1.1 s). Idol takes 6.8 s vs 7.1 s for TRELLIS and 9.9 s for TripoSplat • 262,144 Gaussians, 50 steps: 3.4 s on B300, 6.7 s on H100, 19.1 s on RTX 4090, 46.2 s on a 10 GB RTX 3080 🛠️ Try it • Install idol-sdk, accept the terms of the gated DINOv3 and FLUX.2-dev models, run hf auth login • python -m idol.sample --image photo.jpg --mode real • --num_gaussians runs from 32,768 (0.4 MB) to 1,048,576 (12.2 MB) ⚠️ Caveats • Test set and size are not named, and no independent evaluation exists yet • The card says "under 2 seconds", but the timing table shows 3.4 s at best • Single objects only, NVIDIA CUDA required, no failure cases shown https://huggingface.co/speridlabs/idol https://speridlabs.com/research/idol If you run it on your own messy photos, how do the unseen sides hold up? 📚 Read it elsewhere • The deep dive on Medium: https://medium.com/p/5f660ae6ae56 • The long read on Substack: https://sajjadpakdamansavoji.substack.com/p/speridlabs-idol-builds-3d-splats • The thread on X: https://x.com/saavoji/status/2119137739580858545 • Every version on sajjadpsavoji.github.io: https://sajjadpsavoji.github.io/blog#speridlabs-idol

liked a Space about 5 hours ago

FineEnvs/RL-Explorer

liked a dataset about 6 hours ago

allenai/Dolci-Think-SFT-Clean-v2

View all activity

Organizations

liked a Space about 5 hours ago

RL Environments on Hugging Face

Explore RL environments, browse tasks and run agent rollouts

liked 2 datasets about 6 hours ago

allenai/Dolci-Think-SFT-Clean-v2

Viewer • Updated 4 days ago • 2.05M • 1.29k • 7

NousResearch/arete-data-pairs

Viewer • Updated 2 days ago • 93.4k • 642 • 43

liked 7 models about 6 hours ago

klein-ml/Klein-TTS-X1.5-Pro

Text-to-Speech • 13.1M • Updated 5 days ago • 136 • 8

unsloth/gemma-3n-E4B-it-GGUF

Image-Text-to-Text • 7B • Updated Jun 30, 2025 • 47.3k • 209

unsloth/gemma-3-1b-it

Text Generation • 1.0B • Updated May 12, 2025 • 51.3k • • 23

unsloth/orpheus-3b-0.1-ft

Text-to-Speech • 3B • Updated Jul 9, 2025 • 45.3k • 17

unsloth/gemma-3n-E2B-it-GGUF

Image-Text-to-Text • 4B • Updated Jul 17, 2025 • 45.8k • 64

unsloth/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF

Image-Text-to-Text • 2B • Updated 24 days ago • 46.2k • 67

unsloth/embeddinggemma-300m

Sentence Similarity • 0.3B • Updated Jan 22 • 62.5k • 13

liked a model about 16 hours ago

unsloth/Qwen3.8-Flash-Next-GGUF

Image-Text-to-Text • 177B • Updated 1 day ago • 1.55M • 1.53k

liked 2 models 1 day ago

EAGLE-Corp/Qwen3.8-27B-EAGLE4

3B • Updated 20 days ago • 2.75k • 20

baidu/Unlimited-OCR-2

Image-Text-to-Text • 3B • Updated 7 days ago • 391k • 654

liked 2 datasets 1 day ago

codepawl/abo-glb

Viewer • Updated 1 day ago • 7.95k • 23.9k • 98

TheAgenticDataCompany/open-yap-1k

Viewer • Updated 19 days ago • 16 • 6.88k • 194

liked 2 models 1 day ago

xiaomi-research/Xiaomi-OCR-0

Image-Text-to-Text • 0.9B • Updated 11 days ago • 24.6k • 311

LiquidAI/LFM3-1.7B-Base

Text Generation • 2B • Updated 6 days ago • 8.94k • 152

liked a dataset 1 day ago

LiquidAI/antidoom-mix-v1.0

Preview • Updated Jul 28 • 300 • 125

liked 2 models 1 day ago

PrunaAI/P-H3-Image

Text-to-Image • 33B • Updated 5 days ago • 893 • 170

Cactus-Compute/whistle

Automatic Speech Recognition • Updated 3 days ago • 86.4k • 563