geronimo's picture

geronimo PRO

g-ronimo

·

https://medium.com/@geronimo7

geronimi73

AI & ML interests

fafo

Recent Activity

reacted to Xenova's post with 🔥 12 days ago

Okay this is insane... WebGPU-accelerated semantic video tracking, powered by DINOv3 and Transformers.js! 🤯 Demo (+ source code): https://huggingface.co/spaces/webml-community/DINOv3-video-tracking This will revolutionize AI-powered video editors... which can now run 100% locally in your browser, no server inference required (costs $0)! 😍 How does it work? 🤔 1️⃣ Generate and cache image features for each frame 2️⃣ Create a list of embeddings for selected patch(es) 3️⃣ Compute cosine similarity between each patch and the selected patch(es) 4️⃣ Highlight those whose score is above some threshold ... et voilà! 🥳 You can also make selections across frames to improve temporal consistency! This is super useful if the object changes its appearance slightly throughout the video. Excited to see what the community builds with it!

liked a model about 1 month ago

Qwen/Qwen-Image

upvoted a paper about 1 month ago

MetaCLIP 2: A Worldwide Scaling Recipe

View all activity

Organizations

liked 2 models about 1 month ago

Qwen/Qwen-Image

Text-to-Image • Updated 18 days ago • 172k • • 1.97k

fofr/kontext-make-person-real

Image-to-Image • Updated Jul 20 • 868 • • 74

liked 2 models about 2 months ago

somanchiu/reswapper

Updated Jul 20 • 12

jeiku/moondream2-onnx-bnb4

Image-Text-to-Text • Updated Jun 24, 2024 • 2 • 1

liked a model 3 months ago

onnx-community/ModernBERT-base-ONNX

Fill-Mask • Updated Jun 7 • 1 • 2

liked 5 models 4 months ago

ooutlierr/fuse-dit

Text-to-Image • Updated May 19 • 2 • 8

nielsr/my-awesome-nanovlm-model

Image-Text-to-Text • 0.2B • Updated May 6 • 5 • 1

mrfakename/qwen3-0.6b-writing

0.6B • Updated Apr 30 • 7 • 2

Qwen/Qwen3-0.6B

Text Generation • 0.8B • Updated Jul 26 • 4.08M • • 592

ostris/Flex.2-preview

Text-to-Image • Updated Apr 25 • 1.52k • 373

liked 5 models 5 months ago

mirth/chonky_distilbert_base_uncased_1

Token Classification • 0.1B • Updated Apr 26 • 18.7k • 12

VisualCloze/VisualCloze

Image-to-Image • Updated May 18 • 15

ShoufaChen/PixelFlow-Text2Image

Text-to-Image • Updated Apr 12 • 13

HuggingFaceTB/SmolVLM-256M-Instruct

Image-Text-to-Text • 0.3B • Updated Apr 8 • 292k • 280

ostris/Flex.1-alpha-Redux

Text-to-Image • Updated May 17 • 1.91k • 114

liked 2 datasets 5 months ago

X-ART/LeX-10K

Viewer • Updated Apr 6 • 9.9k • 229 • 27

zhang0jhon/Aesthetic-4K

Viewer • Updated Jun 4 • 2.7k • 2.83k • 28

liked 2 models 6 months ago

stabilityai/stable-virtual-camera

Image-to-Video • Updated Jun 3 • 25.8k • 213

mit-han-lab/dc-ae-f32c32-sana-1.1-diffusers

Text-to-Image • Updated Feb 2 • 1.22k • 6

liked a dataset 6 months ago

gmongaras/CC12M_and_Imagenet21K_Recap

Viewer • Updated Feb 21 • 22.7M • 517 • 6