Qwen-Image-Layered decomposes images into transparent RGBA layers, unlocking inherent editability. You can move, resize, or delete objects without artifacts. Supports recursive decomposition and variable layer counts.
This is a really interesting release from the Qwen team. The model natively decomposes images into layers, which is basically the foundation for any precise editing work.
It is fine-tuned based on Qwen-Image. Right now, the Hugging Face demo allows splitting up to 10 layers, which is usually enough for most workflows.
The model size is a bit heavy. Hopefully, we will see a lighter or distilled version in the future!
About Qwen-Image-Layered on Product Hunt
“Turn flat images into multi-layer editable assets”
Qwen-Image-Layered launched on Product Hunt on December 22nd, 2025 and earned 267 upvotes and 11 comments, placing #4 on the daily leaderboard. Qwen-Image-Layered decomposes images into transparent RGBA layers, unlocking inherent editability. You can move, resize, or delete objects without artifacts. Supports recursive decomposition and variable layer counts.
On the analytics side, Qwen-Image-Layered competes within Open Source, Artificial Intelligence and Photo editing — topics that collectively have 535.9k followers on Product Hunt. The dashboard above tracks how Qwen-Image-Layered performed against the three products that launched closest to it on the same day.
Who hunted Qwen-Image-Layered?
Qwen-Image-Layered was hunted by Zac Zuo. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Zac Zuo
Hi everyone!
This is a really interesting release from the Qwen team. The model natively decomposes images into layers, which is basically the foundation for any precise editing work.
It is fine-tuned based on Qwen-Image. Right now, the Hugging Face demo allows splitting up to 10 layers, which is usually enough for most workflows.
The model size is a bit heavy. Hopefully, we will see a lighter or distilled version in the future!