Open source Nano-banana is here!
The release of Qwen Image Edit 2509 provides AI filmmakers with a powerful, free, open-source alternative for detailed image editing and character consistency.
What this lesson covers
This video covers the release and tutorial of Qwen Image Edit 2509, a free and open-source image editor developed by Alibaba. The host tests its capabilities against closed-source competitors like Cadream and Nano Banana across tasks like pose control, object removal, and depth estimation.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 0:10 ↗
Alibaba released Qwen Image Edit 2509 as a free, open-source image editing model capable of local offline execution.
- 2:03 ↗
The model features built-in control net functionality allowing users to guide output character poses using pose skeleton references.
- 6:29 ↗
Qwen Image Edit 2509 successfully isolates and removes specific objects, such as individual white geese, while leaving other animals intact.
- 8:11 ↗
The model can generate accurate depth maps from input images, detecting subtle background elements.
Workflow outlined in the video
- Download Qwen Image Edit 2509 models from Hugging Face or run them via ComfyUI.
- Test pose-controlled image generation by uploading a reference character and a pose skeleton.
- Experiment with clothing swaps and multi-object removal on complex reference photos.
- Compare generation results and detail preservation against commercial tools like Nano Banana.
Before you use this workflow
These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.
ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.
Explore the tools
How to interpret the numbers
596,445 views captured 23 October 2026. ReelStack recommendation score: 66/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 45% performance: 5.81× views vs 6 other channel videos observed at a similar age. View-evidence factor 100% (views / (views + 1,000))
- 25% freshness: 0/100 with a 14-day half-life
- 20% momentum: 536 views/day vs 3 channel baseline (6 comparable uploads), with the same view-evidence factor
- 10% engagement: 74/100; likes + 4× comments, smoothed with a 500-view neutral prior