A MOSS-Image LoRA model trained across three training runs, totaling 9,000 steps, using 100 original illustrations by Rubi-sama

This model was trained using the training environment and computing resources provided by the AIGC section of the ModelScope community (Model Training)

• Model Type: LoRA

• Base Model: openmoss/MOSS-Image-SFT

• Training Framework: DiffSynth-Studio

• Training Dataset Size: 100 samples

• Total Training Steps: 9000

• License: Apache-2.0