【Sentimental Sentiments】Hanfu Photography SD1.5LoRA-Uncle Martin
V1


















【Sentiment】Hanfu Photography LoRA
Beautiful Hanfu photography.
Based on the modeling training of Martin Fashion, please use it under this big model
Recommended Fujifilm PRO400 H tag tones.
Sampler: DPM++ 3M SDE Exponential Step around 40
Lora weight 0.7-0.8
Although it is 1.5, try to use 1024 as the long side for the output the materials are all high-definition images, enlarging from 512 will lose detail
Trigger word: hanfu girl
Scenes for shooting include spring, summer, autumn, winter, seaside, bamboo forest, regular landscapes, etc. Tried traditional poetic images from the recommended images, seems suitable for Chinese painting style photography and some fantasy styling.
After all, "Martin Fashion" is a versatile large model that can try generalizing other effects. Everyone needs to experiment more.
This model requires friends who are good at editing to play with it. Otherwise, the weight needs to be reduced, or else it's time to draw cards.
Because Hanfu girls show their hands too little haha
Negative words
Use these phrases for photos:
bad-picture-chill-75v,ng_deepnegative_v1_75t,(badhandv4:1.2),(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4),text,close up,cropped,out of frame,worst quality,low quality,jpeg artifacts,ugly,duplicate,morbid,mutilated,extra fingers,mutated hands,poorly drawn hands,poorly drawn face,mutation,deformed,blurry,dehydrated,bad anatomy,bad proportions,extra limbs,cloned face,disfigured,gross proportions,malformed limbs,missing arms,missing legs,extra arms,extra legs,fused fingers,too many fingers,(long neck),
For some special effects, use:
bad-picture-chill-75v,ng_deepnegative_v1_75t,(badhandv4:1.2),low quality,watermark,text,bad anatomy,bad hand,extra hands,extra fingers,(extra digit and hands and fingers and legs and arms),(deformed fingers),extra legs,lowres,bad anatomy,bad hands,text,error,missing fingers,fewer digits,cropped,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,username,blurry,
Tried Animediff
The large model "Martin Fashion" is very suitable for making live videos, supports 1024 direct output, does not have double heads, also looks good with Hanfu lora, the cover is made by Wen Sheng, not generated by the image.
Can relatively stably produce a 4-second video.
QQ: 2173614854
Red Book: 2973981829
TikTok: 33696886986
C Station: Uncle_Martin1977
