Finally! New best local AI image editor is here
AI Search showed 6 AI tools in this video on . 3 are verified available in the EU. Each row below jumps to the exact second. Part of week 2026-39.
Tools shown in this video, with timestamps
Open-source image generator and editor from Alibaba that supports text-to-image, transparent (alpha channel) output, and editing with up to 10 reference images. Creator walks through ComfyUI install, text-to-image, image edit and background removal workflows, with quantized versions running on 8 GB or less VRAM. Licence is non-commercial, but Qwen says outputs can be used commercially.
Live demoNode-based interface used to run Qwen Image 2.1 locally. Creator shows updating it, using the templates, and loading models and LoRAs.
Live demoSponsor segment: agents that work across creative workflows, from concept to assets, while remembering project context.
Luma's latest video model, described in the sponsor segment as strong on motion, physics and 3D space.
The only LoRA available so far for Qwen Image 2.1, meant to improve character consistency in anime-style editing. Creator loads it into the edit workflow and generates a character reference sheet.
Live demoCommunity GGUF quantized versions of Qwen Image 2.1, the smallest at 3.19 GB, for GPUs with about 4 GB VRAM. Creator tests the Q3 version through the GGUF loader node and finds quality similar to the full model.
Live demo