nodes/cubiq-ComfyUI_IPAdapter_plus
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

updated documentation

Browse Source
This commit is contained in:
matt3o
2023-09-07 18:26:04 +02:00
parent c25183e9ff
commit 0685e0545b
1 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7 -3
View File
@@ -1,5 +1,3 @@
**ALPHA STAGE! Not production ready!**
# ComfyUI_IPAdapter_Plus
ComfyUI reference implementation for [IPAdapter](https://github.com/tencent-ailab/IP-Adapter/tree/6fb9d3554a5c774f41e187e8fdbc7b9a1db8c2e3) models.
@@ -29,4 +27,10 @@ Additionally you need the clip vision models:
- SD 1.5: [pytorch_model.bin](https://huggingface.co/h94/IP-Adapter/resolve/main/models/image_encoder/pytorch_model.bin)
- SDXL: [pytorch_model.bin](https://huggingface.co/h94/IP-Adapter/resolve/main/sdxl_models/image_encoder/pytorch_model.bin)
You can rename them to something easier to remember (eg: `ip-adapter_sd15-image-encoder.bin`) and place them under `ComfyUI/models/clip_vision/`.
You can rename them to something easier to remember (eg: `ip-adapter_sd15-image-encoder.bin`) and place them under `ComfyUI/models/clip_vision/`.
## How to use
There are two workflows included in this repo.
**IMPORTANT:** To use the *IPAdapter Plus* model you must use the new `CLIP Vision Encode (IPAdapter)` node (the workflow is [Plus_workflow.json](./Plus_workflow.json)). The non-plus version works with both the standard `CLIP Vision Encode` and the new one.