alkinun

AtAndDev

·

https://baretile.com/

alkinun

AI & ML interests

decentralize

Recent Activity

reacted to savoji's post with 🔥 about 5 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 8 hours ago

FineEnvs/RL-Explorer

liked a dataset about 8 hours ago

allenai/Dolci-Think-SFT-Clean-v2

View all activity

Organizations

AtAndDev 's models 20

AtAndDev/UVOX-Magpie-xLAM-Supernova-8B

0.7B • Updated Oct 30, 2025 • 11

AtAndDev/Magpie-xLAM-Supernova-8B

Text Generation • 8B • Updated Oct 30, 2025 • 13 • 1

AtAndDev/UVOX-xLAM-2-8B

0.7B • Updated Oct 25, 2025 • 12

AtAndDev/UVOX-96k-Llama-32-3B-Instruct

Audio-Text-to-Text • 49.6M • Updated Oct 25, 2025 • 25

AtAndDev/UVOX-40k-Llama-32-3B-Instruct

Audio-Text-to-Text • 49.6M • Updated Oct 23, 2025 • 29

AtAndDev/UVOX-12k-Llama-32-3B-Instruct

Audio-Text-to-Text • 49.6M • Updated Oct 23, 2025 • 23

AtAndDev/UVOX-95k-Llama-3.2-1B-Instruct

Audio-Text-to-Text • 46.1M • Updated Oct 21, 2025 • 29

AtAndDev/UVOX-90k-Llama-3.2-1B-Instruct

Audio-Text-to-Text • 46.1M • Updated Oct 21, 2025 • 40

AtAndDev/UVOX-50k-Llama-3.2-1B-Instruct

Audio-Text-to-Text • 46.1M • Updated Oct 21, 2025 • 32

AtAndDev/UVOX-5k-Llama-3.2-1B-Instruct

Audio-Text-to-Text • 46.1M • Updated Oct 20, 2025 • 33

AtAndDev/UVOX-Qwen3-4B-Instruct-2507

Audio-Text-to-Text • 47.2M • Updated Oct 20, 2025 • 25

AtAndDev/SelfCoder-v0.0

Text Generation • 4B • Updated May 19, 2025 • 15

AtAndDev/lora_model

Updated Apr 5, 2025

AtAndDev/marco-qwq-7B

Text Generation • 8B • Updated Dec 8, 2024 • 21

AtAndDev/Ogno-Monarch-Neurotic-9B-Passthrough

Text Generation • 9B • Updated Mar 1, 2024 • 60

AtAndDev/Ogno-Monarch-Neurotic-7B-Dare-Ties

Text Generation • 7B • Updated Mar 1, 2024 • 57

AtAndDev/Marcoro14-7B-Slerp

Text Generation • 7B • Updated Mar 1, 2024 • 6

AtAndDev/CapybaraMarcoroni-7B

Text Generation • 7B • Updated Jan 7, 2024 • 57

AtAndDev/ShortKing-3b-v0.2

Text Generation • 3B • Updated Oct 2, 2023 • 60 • 2

AtAndDev/ShortKing-1.4b-v0.1

Text Generation • 1B • Updated Sep 29, 2023 • 43 • 2