Thank you for support my work. https://www.buymeacoffee.com/bdsqlsz Support list will show in main page. Support List Pre trained models and output samples of ControlNet LLLite form bdsqlsz Inference with ComfyUI: https://github.com/kohya ss/ControlNet LLLite ComfyUI Not Controlnet Nodes! For 1111's Web UI, sd webui controlnet extension supports ControlNet LLLite. Training: https://github.com/kohya ss/sd scripts/blob/sdxl/docs/train lllite README.md The recommended preprocessing for the animeface model is Anime Face Segmentation Models Trained on anime model AnimeFaceSegment、Normal、T2i Color/Shuffle、lineart anime denoise、recolor luminance Base Model useKohaku XL MLSD Base Model useProtoVision XL High Fidelity 3D Japanese Introduction https://note.com/kagami kami/n/nf71099b6abe3 Thank kgmkm mkgm for introducing these controlllite models and testing. Samples AnimeFaceSegmentV2 DepthV2 (Marigold) MLSDV2 Normal Dsine T2i Color/Shuffle Lineart Anime Denoise Recolor Luminance Canny DW OpenPose Tile Anime 和其他模型不同，我需要简单解释一下tile模型的用法。 总的来说，tile模型有三个用法， 1、不输入任何提示词，它可以直接还原参考图的大致效果，然后略微重新修改局部细节，可以用于V2V。(图2) 2、权重设定为0.55~0.75,它可以保持原本构图和姿势的基础上，接受提示词和LoRA的修改。(图3) 3、使用配合放大效果，对每个tiling进行细节增加的同时保持一致性…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy