Based on the fine-tuning style of v1.0, it is more in line with a certain look and feel. The basic training resolution is 832*832.
So you can output the image at a slightly larger resolution, and can use 640 as the short side.
Start: masterpiece, best quality,
Example negative prompt words:
artist name, watermark, signature, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, few digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name worst quality, low quality, swollen or deformed toes, overlapping toes, excess toenail, incorrect toe count, uneven toe count, unnatural foot proportions,
Use the style of fine-tuning the xl data set. I haven't played 1.5 for a long time, so you can debug it yourself when you print.
Based on the fine-tuning style of v1.0, it is more in line with a certain look and feel. The basic training resolution is 832*832.
So you can output the image at a slightly larger resolution, and can use 640 as the short side.
Start: masterpiece, best quality,
Example negative prompt words:
artist name, watermark, signature, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, few digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name worst quality, low quality, swollen or deformed toes, overlapping toes, excess toenail, incorrect toe count, uneven toe count, unnatural foot proportions,
Use the style of fine-tuning the xl data set. I haven't played 1.5 for a long time, so you can debug it yourself when you print.