Hiring 💼

1 33

ddddx

lu774067819

AI & ML interests

None yet

Recent Activity

liked a model about 1 month ago

zai-org/GLM-5

liked a model 4 months ago

oumoumad/Qwen-Edit-2509-Material-transfer

liked a model 4 months ago

peteromallet/Qwen-Image-Edit-InScene

View all activity

Organizations

None yet

liked a model about 1 month ago

zai-org/GLM-5

Text Generation • 754B • Updated about 19 hours ago • 148k • • 1.86k

liked 2 models 4 months ago

oumoumad/Qwen-Edit-2509-Material-transfer

Image-to-Image • Updated Dec 2, 2025 • 35

peteromallet/Qwen-Image-Edit-InScene

Image-to-Image • Updated Nov 1, 2025 • 2.24k • 89

liked a model 6 months ago

rockerBOO/flux.1-dev-SRPO

Text-to-Image • Updated Oct 8, 2025 • 854 • 72

liked a model 9 months ago

orabazes/depth_lora_kontext

Updated Jun 30, 2025 • 30

reactedto ZhengPeng7's post with 👍 11 months ago

Post

7428

We just released the [BiRefNet_HR]( ZhengPeng7/BiRefNet_HR) for general use on higher resolution images, which was trained with images in 2048x2048. If your images are mostly larger than 1024x1024, use BiRefNet_HR for better results! Thanks to @Freepik for the kind support of H200s for this huge training.

HF Model: ZhengPeng7/BiRefNet_HR.
HF Demo: ZhengPeng7/BiRefNet_demo, where you need to choose General-HR and set high resolution.
PyTorch weights & ONNX: in Google Drive and the GitHub release.

Here is a comparison between the results of the original one and the new HR one on HR inputs:

And, the performance of this new HR one and the previous one trained in 1024x1024 on val set:

liked a model 12 months ago

lldacing/flash-attention-windows-wheel

Updated May 31, 2025 • 315

liked 2 models about 1 year ago

wei112/ziyong

Updated Aug 8, 2024 • 2

whitealan/WhitePony

Updated Dec 29, 2024 • 22

liked a model over 1 year ago

mattmdjaga/segformer_b2_clothes

Image Segmentation • 27.4M • Updated Sep 19, 2025 • 375k • • 491

liked a Space over 1 year ago

BRIA RMBG 2.0

🐢

897

remove background from any image

reactedto clem's post with ❤️ over 1 year ago

Post

3744

Very few people realize that most of the successful AI startups got successful because they were focused on open science and open-source for at least their first few years. To name but a few, OpenAI (GPT, GPT2 was open-source), Runway & Stability (stable diffusion), Cohere, Mistral and of course Hugging Face!

The reasons are not just altruistic, it's also because sharing your science and your models pushes you to build AI faster (which is key in a fast-moving domain like AI), attracts the best scientists & engineers and generates much more visibility, usage and community contributions than if you were 100% closed-source. The same applies to big tech companies as we're seeing with Meta and Google!

More startups and companies should release research & open-source AI, it's not just good for the world but also increases their probability of success!