在没有触发词的情况下,推荐权重1.5到2,有触发词ghibli的情况下,推荐权重1到1.5。没有生成信息的原因是我是用comfyui生成的图像,需要将原图像拖拽到comfyui的工作台才能读取生成参数
If you dont wanna use the trigger word, the recommended weight is 1.5 to 2.5, and in the case of the use of trigger word ghibli, the recommendation weight is 1 to 1.5.
The reason why there is no generated information is that I am using the image generated by comfyui, and you need to drag and drop the original image to the comfyui workbench to read the generation information.
对比图
Comparison chart


prompt: background,ghibli, misty world, wonder land and full of fantasy animals but no human
nagative: lowres, (((bad anatomy))), (bad hands), text,error, missing fngers,extra digt ,fewer digits,cropped, wort quality ,low quality,normal quality, jpeg artifacts,signature,watermark, username, blurry, (((bad feet))), poorly drawn hands, poorly drawn face, mutation, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, more than 2 nipples, out of frame, ugly, extra limbs, bad anatomy, gross proportions, {malformed limbs}, missing arms, missing legs, extra arms, extra legs, mutated hands, fused fingers, too many fingers, long neck, missing fingers, extra digit, fewer digits, bad feet,lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, an6, AuroraNegative, bad-picture-chill-75v, badhandv4, deformityv6, EasyNegative, FastNegativeEmbedding, KHFB, negative_hand-neg, ng_deepnegative_v1_75t, verybadimagenegative_v1.3,
model: sdxl_base_1.0
Description
FAQ
Comments (9)
Hi, i use A1111 and in Base SDXL work good, but when I send img to img2img and switch REFINEMENt model i have error
( RuntimeError: The size of tensor a (768) must match the size of tensor b (640) at non-singleton dimension 1)
在哪下载带有workflow的原图?civitai是支持读取comfyui生成信息的,但您提供的图片没有附带这些信息。
An observation and Question: In your example negative prompt there are a lot of SD15 inversions. Do you find that prompting those helps as token, even if they can't be loaded?
i ve looked but couldnt figure it out how to use this lora in krita ai to turn real photos into ghibli style, can any one give me the receipt, thanks.







