How to use InvokeAI/ip_adapter_sd_image_encoder with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, CLIPVisionModelWithProjection tokenizer = AutoTokenizer.from_pretrained("InvokeAI/ip_adapter_sd_image_encoder") model = CLIPVisionModelWithProjection.from_pretrained("InvokeAI/ip_adapter_sd_image_encoder", device_map="auto")
