ModelScope ships LayerExtract and LayerRemove LoRAs for clean object layer editing
bdsqlsz · x · 2026-09-28
- ModelScope released two compact Qwen-Image-2.1 LoRAs: LayerExtract isolates a prompt-specified subject as a transparent layer; LayerRemove removes that object from the source image and reconstructs the scene behind it.
- Both hot-swap within the same DiffSynth-Studio pipeline, turning flattened images into editable assets for compositing, repositioning, and replacement workflows.
- LoRA weights are Apache 2.0 licensed, subject to Qwen-Image-2.1 base-model terms.
Related event: Qwen-Image-2.1 Gets Layer Extraction and Removal LoRAs(2 posts)→
More from Multimodal
- Filmworkbench v0.1.2: one-prompt semi-automated short films with Claude and ComfyUI — Eastern-Ad9515 · 2026-11-16
- Seedance 2.5 Flash Generates Intense Fight Scene From Just 2 Random Images — aziz4ai · 2026-11-16
- A video editor tested free MCP-connected AI editing tools: invideo, ChatCut, FableCut — lol_you_again · 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