New Qwen-Image-2.1 LoRA blends styles from two input images
bdsqlsz · x · 2026-09-22
Japanese creator @8co28 released a LoRA for Qwen-Image-2.1 (an update to their QIE2509-2511 LoRA from late last year): feed it two images and it can mix the two art styles, or generate entirely new artwork in the blended style.
Prompts control composition—e.g., plain "mix" for panels 2/4, plus "front view" for 1 and "squatting" for 3.
More from Multimodal
- Krea-2-Turbo v2 demo space trends on Hugging Face — Jackiesixnine · 2026-09-22
- Generating Dragon Ball-style animation with Minimax H3 on a 24GB RTX 3090 — FigN3wton · 2026-09-22
- Using Minimax H3 as an image-edit model: settings and banding tips? — ItwasCompromised · 2026-09-22
- Midjourney v8.2 demo: "Machine Make Machine" generated image — chrisfirst · 2026-09-22
- Grok 4.7 vs 4.6 Blender render comparison shows clear gains in shadows and texture — mattyp · 2026-09-22
- Pika unveils new AI creative platform with Relight tool that re-lights any photo or video — aziz4ai · 2026-09-22