
When generating high-precision images, it can capture details, textures, and light-shadow changes more delicately. With a strong understanding of prompts, the generated images have a higher degree of matching with the textual content.Everyone is also welcome to share their results.
To achieve the best image quality, please follow the parameter configuration below for setup.
1. Sampling recommendation: DPM 2M, Step 55 40
2. Resolution: 1080*1400 (recommended), 1080*1374
4. Prompt guidance coefficient (CFG Scale) 0.35
5. Negative prompts: (((Open mouth:2)))),(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,badhandv4,ng_deepnegative_v1_75t,(bad hands 5:0.6)
When generating high-precision images, it can capture details, textures, and light-shadow changes more delicately. With a strong understanding of prompts, the generated images have a higher degree of matching with the textual content.Everyone is also welcome to share their results.
To achieve the best image quality, please follow the parameter configuration below for setup.
1. Sampling recommendation: DPM 2M, Step 55 40
2. Resolution: 1080*1400 (recommended), 1080*1374
4. Prompt guidance coefficient (CFG Scale) 0.35
5. Negative prompts: (((Open mouth:2)))),(worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,badhandv4,ng_deepnegative_v1_75t,(bad hands 5:0.6)