Ostris AI Toolkit adds Qwen-Image-2.1 training with native alpha channel support
ostrisai · x · 2026-09-21
Ostris announced that its open-source AI Toolkit now supports training Qwen-Image-2.1, including native alpha channel support.
The author tested it on a small t-shirt design dataset: no trigger word or dedicated alpha text was needed—just default sample prompts—and results looked good after only 750 training steps. Native alpha support, he argues, unlocks many new workflows for transparent assets, stickers, and print design.
Related event: Ostris AI Toolkit Adds Qwen-Image-2.1 LoRA Training Support(3 posts)→
More from Multimodal
- Turn any video into volumetric playback with exportable 360° orbits at custom tempo — LinusEkenstam · 2026-09-21
- Full Krea2 concept-art pipeline: four custom LoRAs, 5MP native frames, two-step upscale to 7000px — Dacrikka · 2026-09-21
- Phone video in, navigable 3D room out: K3-powered splat pipeline runs in the browser — willeastcott · 2026-09-21
- Viral Arabic AI trick: upload a photo and your name to get a magazine-cover portrait — aziz4ai · 2026-09-21
- MURAL METAMORPHOSIS: a fill-in prompt template that turns any subject into street-art murals — LudovicCreator · 2026-09-21
- Dreamina launches rebuilt web experience with film-grade workflows and unified canvas — Uncanny_Harry · 2026-09-21