sd-webui 更新到了1.6,支持在文生图和图生图中直接使用Refiner,无需分开使用了。
这里的切换时机,指的是从迭代步数的多少开始介入。如迭代步数设置为30,切换时机为0.8,则refiner在(30*0.8)24步开始介入绘画。
sd webui 1.6也更新了更多的采样器
这部分等空下来了分别测试看看效果。
言归正传,controlNet版本更新到1.1.4以后,开始支持SDXL大模型,按照作者的说法是这个版本是针对webui 1.6开发的,新的模型如下:
- diffusers_xl_canny_full.safetensors
- diffusers_xl_canny_mid.safetensors
- diffusers_xl_canny_small.safetensors
- diffusers_xl_depth_full.safetensors
- diffusers_xl_depth_mid.safetensors
- diffusers_xl_depth_small.safetensors
- ioclab_sd15_recolor.safetensors
- ip-adapter_sd15.pth
- ip-adapter_sd15_plus.pth
- ip-adapter_xl.pth
- kohya_controllllite_xl_depth_anime.safetensors
- kohya_controllllite_xl_canny_anime.safetensors
- kohya_controllllite_xl_scribble_anime.safetensors
- kohya_controllllite_xl_openpose_anime.safetensors
- kohya_controllllite_xl_openpose_anime_v2.safetensors
- sai_xl_canny_128lora.safetensors
- sai_xl_canny_256lora.safetensors
- sai_xl_depth_128lora.safetensors
- sai_xl_depth_256lora.safetensors
- sai_xl_recolor_128lora.safetensors
- sai_xl_recolor_256lora.safetensors
- sai_xl_sketch_128lora.safetensors
- sai_xl_sketch_256lora.safetensors
- sargezt_xl_depth.safetensors
- sargezt_xl_depth_faid_vidit.safetensors
- sargezt_xl_depth_zeed.safetensors
- sargezt_xl_softedge.safetensors
- t2i-adapter_xl_canny.safetensors
- t2i-adapter_xl_openpose.safetensors
- t2i-adapter_xl_sketch.safetensors
- thibaud_xl_openpose.safetensors
- thibaud_xl_openpose_256lora.safetensors
支持revision (SDXL)和reference (SDXL)但不需要额外的模型。
上述模型下载地址:https://huggingface.co/lllyasviel/sd_control_collection/tree/main
安装方法还是跟之前一样,放到controlnet的models下即可
值得注意的是,自从sdxl大模型发布以来,以前跑的动的机器都跑不动了,虽然后来又做了优化,现在又把controlnet的模型加进去,最好还是把低显存模式开启了,省的爆显存又得折腾半天。
有了controlnet的加持,sdxl才算是接近完整,否则,还不如1.5下继续呢