下载的lora模型是ip-adapter-faceid-plusv2_sd15_lora.safetensors,把它放到/ComfyUI/models/loras 然后下载clip_h.pth和buffalo_l.zip: 下载clip_h.pth:https://huggingface.co/h94/IP-Adapter/resolve/main/models/image_encoder/model.safetensors,放到/ComfyUI/models/clip_vision,将文件名改为CLIP-ViT-...
A节点,IPAdapterModelLoader节点,加载ip-adapter-faceid_sd15.bin模型,需要选择你在ComfyUI\models\ipadapter文件夹下模型文件 B节点,CLIPVisionLoader节点,加载ComfyUI\models\clip_vision的IMG encoder,这个模型只有两个1.5版本的VIT-H,XL版本的VIT-G,但是需要注意的是有一部分XL模型是基于1.5 encoder训练的,所以大...
"ip-adapter-plus_sd15.bin" "IPAdapter_image_encoder_sd15.safetensors" ] }, { "id": 5, "type": "IPAdapterApply", "id": 3, "type": "IPAdapterModelLoader", "pos": [ 650, 290, 60 ], "size": { "0": 210, "1": 142 "0": 300, "1": 60 }, "flags": {}, "order"...
"IPAdapter_image_encoder_sd15.safetensors" ] } ], "links": [ 339 changes: 174 additions & 165 deletions 339 examples/IPAdapter_face.json Load diff Large diffs are not rendered by default. 277 changes: 143 additions & 134 deletions 277 examples/IPAdapter_inpaint.json Original f...
"IPAdapter_image_encoder_sd15.safetensors" ] }, { "id": 7, "type": "CLIPTextEncode", "pos": [ 360, 120 ], "size": { "0": 380, "1": 160 }, "flags": {}, "order": 7, "mode": 0, "inputs": [ { "name": "clip", "type": "CLIP...
ip-adapter-plus-face_sd15.safetensors, Face model, portraits ip-adapter-full-face_sd15.safetensors, Stronger face model, not necessarily better ip-adapter_sd15_vit-G.safetensors, Base model, requires bigG clip vision encoder ip-adapter_sdxl_vit-h.safetensors, SDXL model ip-adapter-plus...
https://huggingface.co/h94/IP-Adapter/resolve/main/sdxl_models/ip-adapter-plus-face_sdxl_vit-h.bin 此外，您需要将图像编码器放置在ComfyUI/models/clip_vision/目录中:https://huggingface.co/h94/IP-Adapter/resolve/main/models/image_encoder/model.safetensors https://huggingface.co/h94/IP-...
https://huggingface.co/h94/IP-Adapter/resolve/main/sdxl_models/ip-adapter-plus-face_sdxl_vit-h.bin 以上8个,需要全部下载。 此外,您需要将图像编码器放置在ComfyUI/models/clip_vision/目录中: https://huggingface.co/h94/IP-Adapter/resolve/main/models/image_encoder/model.safetensors ...
image_encoder_path = "laion/CLIP-ViT-H-14-laion2B-s32B-b79K" ip_ckpt = "ip-adapter-faceid-plus_sd15.bin" if not v2 else "ip-adapter-faceid-plusv2_sd15.bin" device = "cuda" noise_scheduler = DDIMScheduler( num_train_timesteps=1000, beta_start=0.00085, beta_end=0.012, beta_...
image_encoder_path = "laion/CLIP-ViT-H-14-laion2B-s32B-b79K" ip_ckpt = "ip-adapter-faceid-plus_sd15.bin" if not v2 else "ip-adapter-faceid-plusv2_sd15.bin" device = "cuda" noise_scheduler = DDIMScheduler( num_train_timesteps=1000, beta_start=0.00085, beta_end=0.012, beta_...