In txt2img, you will only get low quality results due to the training data's quality being bad.
Please use img2img without the LoRA to fix the quality issue.
You can't get the same quality in just one generation.
My workflow:
-
txt2img for base image.
-
img2img + 2x upscale without the lora to fix glitches.
-
img2img + 2x upscale with the lora to enhance details.
描述:
训练词语:
名称: 696844_training_data.zip
大小 (KB): 1027
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: Eve_-_Cybernetic_Dress.safetensors
大小 (KB): 223100
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
原文链接：https://1111down.com/1080766.html，转载请注明出处
