Just 2,305 new params: open-source LoRA teaches FLUX.2 Klein to cut objects into transparent PNGs
ostrisai · x · 2026-09-30
Developer trmz shared a neat open-source project: teaching FLUX.2 Klein to see transparency and extract foregrounds.
- The model's VAE was widened from RGB to RGBA, adding only 2,305 new parameters out of 84M
- A LoRA trained on FLUX.2 Klein 9B cuts objects out of photos as real transparent PNGs, shadows included
- Fully open source
More from Multimodal
- Seedance 2.5 Flash Generates Intense Fight Scene From Just 2 Random Images — aziz4ai · 2026-11-16
- Runway CEO Predicts Fully AI-Generated Cultural Phenomenon by 2027 — c_valenzuelab · 2026-11-16
- Stunning AI-generated motion-blur portraits with a film-photography feel — azed_ai · 2026-11-16
- A Bauhaus functionalist prompt template for geometric poster-style AI art — LudovicCreator · 2026-11-16
- Vivix W1 video model: 100 ten-second ads for about $5 at $0.005 per second — Aiden_Tech_Ai · 2026-11-16
- User Shares Coral Reef Creation Labeled 'Qwen 4 Max (xhigh)', an Unannounced Model Name — intellectronica · 2026-11-16