raise Exception(“IPAdapter model not found.“)

 IPAdapter模型文件太多了,而节点IPAdapter Unified Loader是通过函数(get_ipadapter_file与get_clipvision_file)预设来加载模型文件,当发生错误“IPAdapter model not found.“时并不指明模型文件名,导致想要有针对性下载需要的模型比较困难,而且加载的模型还与加载的Checkpoint大模型的类型也有关系。

1、IPAdapter model not found

 模型下载链接:

 https://hf-mirror.com/h94/IP-Adapter/tree/main/sdxl_models

https://hf-mirror.com/h94/IP-Adapter/tree/main/models

CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors, download and rename
CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors, download and rename

preset(预置) Checkpoint模型类型 模型文件名(models\ipadapter)
后缀名bin、safetensors
同名选择加载bin
模型文件名(models\clip_vision)
LIGHT - SD1.5 only (low strength) SD15 ip-adapter_sd15_light_v11
ip-adapter_sd15_light
CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
SDXL(不支持)    
STANDARD (medium strength) SD15 ip-adapter_sd15 CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
SDXL ip-adapter_sdxl_vit-h CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
VI-G (medium strength) SD15 ip-adapter_sd15_vit-G CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors
SDXL ip-adapter_sdxl CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors
PLUS (high strength) SD15 ip-adapter-plus_sd15 CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
SDXL ip-adapter-plus_sdxl_vit-h CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
PLUS FACE (portraits) SD15 ip-adapter-plus-face_sd15 CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
SDXL ip-adapter-plus-face_sdxl_vit-h CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
FULL FACE - SD1.5 only(portraits stronger) SD15 ip-adapter-full-face_sd15 CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
SDXL(不支持)    

2、ClipVision model not found

3、LoRA model not found

扫描二维码关注公众号,回复: 17528440 查看本文章

IP 适配器 FaceID-Plus V2 SDXL - 使用什么 CLIP Vision 编码器? ·问题 #265 ·tencent-ailab/IP 适配器 ·GitHub的

猜你喜欢

转载自blog.csdn.net/zslefour/article/details/142598605