The model that can generate images with simple prompts. The following settings are recommended: Sampling method: DPM++ 3M SDE Schedule type: Karras Sampling steps: 30 CFG Scale: 3.0 Negative prompts: embedding:<a target="_blank" rel="ugc" href="https://civarchive.com/models/305043/beyond-sdxl-negative">BeyondSDXLv3</a> embedding:<a target="_blank" rel="ugc" href="https://civarchive.com/models/119032/unaestheticxl-or-negative-ti">unaestheticXL_Alb2</a> If you are using LoRA, the following settings are recommended: Sampling method: Euler Schedule type: Automatic(Exponential) Sampling steps: 30 CFG Scale: 3.0 I merged the following two models Thanks to the model providers <a target="_blank" rel="ugc" href="https://civarchive.com/models/118009?modelVersionId=199325">国风4 GuoFeng4 XL v1.2</a> 65% <a target="_blank" rel="ugc" href="https://civarchive.com/models/142601?modelVersionId=373502">ToonyStark Korean Webtoon XL Lightening</a> 35%

Files with SHA256: e93accbdad603837254906e904ea2ce0d13f088295a664e2a8d95e2053e54f9a