Download
1 variant available
4940 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
150 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2080 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(43)
Feb 24, 2026
Qwen

2560 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1.2K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
5.1K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

License:
Apache 2.0This is my workflow creation page, you can click on the link below to experience it directly.
https://www.runninghub.ai/post/2026223216770945026/?inviteCode=sdhs0trb
Fan benefits,register to get 1000 points,daily login 100 points,play 4090!Experience the super power of 48G.
LoRA Description: This LoRA is fine-tuned on Qwen2-VL-7B-Instruct (Image Edit), utilizing a high-quality dataset of 89 curated HD pairs of 3D Donghua (Chinese Animation) styles.
It excels at converting various input styles—ranging from realistic photos to 2D illustrations—into a high-fidelity 3D aesthetic characterized by vibrant lighting and intricate textures.
Trigger Word:
transform into 3d styleRecommended Strength: 0.8 - 1.0
Key Features: One-click stylization, high-definition output, and excellent composition retention.

