I found a new AI tool Shakker, a best image to image tool. You can try it via https://www.shakker.ai ,it can help you:
-Remix: Upload a picture. Just switch the prompts, and you can create stunning images in the same style.
-Style Transfer: Shakker not only extracts the style,but also switches among various styles.
Besides, Shakker also offers Object Control,Composition Control,Collage Redrawing etc.
中文:
模型介绍:可以将人物照片/建筑。风景照等转换为线稿手绘风格。
建议底模:anything4.5,SD1.5,或者final-prune等2.5D或者二次元动漫模型,出建筑等可以搭配realisticvisonV20等真实模型。
生成建议:人物的预处理器可选择softedge,或者linerart,试具体情况而定,提示词引导系数不需要太高3~6左右即可,采样器可自行尝试,controlnet模式为均衡时更贴近原图,controlnet优先则效果相对较好,但是会和原来的人物有区别,clip层为2,模型权重可看情况加大至1.5也可以。可搭配animeoutline线稿系列,具体各个权重可自行尝试
建议promt:manga,monochrome,sketch,line,greyscale,simple background,
English:
Model introduction: Can be people photos/buildings. Landscape photos etc. are converted to line drawing style.
Suggested bottom model: anything4.5,SD1.5, or final-prune 2.5D or quadratic animation models, out of the building can be used with real models such as realisticvisonV20.
Generate suggestions: The character's preprocessor can choose softedge, or linerart, try the specific situation, the prompt word guidance coefficient does not need to be too high 3~6 or so, the sampler can try on its own, controlnet mode is more close to the original image when the balance, controlnet priority is relatively good. However, it will be different from the original character, the clip layer is 2, and the model weight can be increased to 1.5 depending on the situation. Can be matched with animeoutline line draft series, specific weights can try their own.
suggestion promt:manga,monochrome,sketch,line,greyscale,simple background。