Author: AIGC101

Workflow source: https://openart.ai/workflows/aigc101/flux style transfer better version/lJw1nuyXNaGckheGnvqF

For the clip_vision model of the "load flux ipadapter" node, it is recommended to use this model:
https://huggingface.co/openai/clip vit large patch14/resolve/main/model.safetensors?download=true
After downloading, place it in the .../models/clipvision folder.
Regarding controlenet: it is recommended to use depth anything v2. It is recommended to use hed. Canny is not recommended; when using canny, the lines will be overly constrained. If you use it, lower the weights.

For clip_vision model of "load flux ipadapter" node, I recommends using this model:
https://huggingface.co/openai/clip vit large patch14/resolve/main/model.safetensors?download=true
Just download it and put it in .../models/clipvision folder.
About controlenet: we recommend to use depth anything v2, we recommend to use hed, we don't recommend canny, if you use canny, the line will be framed too much, if you insist, turn down the weights.