EN：

【Large Model/Checkpoint】FLUX.1-dev FP8

【Model Weights】0.8~1 (1 is recommended for single LoRa)

【Trigger Word】nhht

【Sampling Method】Euler

【CFG Scale】3.5

【Sampling Steps】30

【About Training】This model's base model is trained using F.1_dev-fp8

【About Usage】This model follows the official FLUX license

【Training Acknowledgements】This model training received technical support from the Moda Community.

ZH：

【大模型/Checkpoint】FLUX.1-dev FP8

【模型权重】0.8~1（单lora建议直接上1）

【触发词】nhht

【采样方法/Sampler Method】Euler

【提示词引导系数/CFG Scale】3.5

【采样步数/Sampling Steps】30

【关于训练】本模型底模使用F.1_dev-fp8训练

【关于使用】本模型遵循FLUX官方许可证

【训练致谢】本模型训练获得魔搭社区技术支持