ahmed
rezzig
AI & ML interests
None yet
Recent Activity
replied to
davanstrien's
post
about 5 hours ago
I fine-tuned a smol VLM to generate specialized art history metadata!
https://huggingface.co/davanstrien/iconclass-vlm: Qwen2.5-VL-3B trained using SFT to generate ICONCLASS codes (think Dewey Decimal for art!)
Trained with TRL + HF Jobs - single UV script, no GPU needed!
Space to explore predictions on a test set: https://huggingface.co/spaces/davanstrien/iconclass-predictions
Blog soon!
reacted
to
davanstrien's
post
with 👍
about 5 hours ago
I fine-tuned a smol VLM to generate specialized art history metadata!
https://huggingface.co/davanstrien/iconclass-vlm: Qwen2.5-VL-3B trained using SFT to generate ICONCLASS codes (think Dewey Decimal for art!)
Trained with TRL + HF Jobs - single UV script, no GPU needed!
Space to explore predictions on a test set: https://huggingface.co/spaces/davanstrien/iconclass-predictions
Blog soon!
replied to
Benedictat's
post
about 7 hours ago
Tencent HunyuanImage 3.0-Instruct is seriously impressive
skyrocketed to 2nd place globally on the LMArena leaderboard, only trailing Google Nano-banana Pro.
What excites me most is its newly launched image editing and multi-image fusion capabilities
its semantic understanding is rock-solid this Instruct-following capability basically enables one-sentence end-to-end workflows, delivering a dimensionality-reducing boost in efficiency.
Frankly, it nails the pain points of frontline creators: old photo restoration, text modification, even extracting people from multiple images to create group shots. Previously, tweaking the fusion quality took tons of effort, but now the out-of-the-box realism and emotional expression are top-tier zero cheap AI artifacts
👉 Repo: https://hunyuan.tencent.com/chat/HunyuanDefault?from=modelSquare&modelId=Hunyuan-Image-3.0-Instruct
technical report：https://arxiv.org/abs/2509.23951
Organizations
None yet