Instructions to use InvokeAI/ip_adapter_sd_image_encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use InvokeAI/ip_adapter_sd_image_encoder with Transformers:
# 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") - Notebooks
- Google Colab
- Kaggle
| license: apache-2.0 | |
| This is the Image Encoder required for SD1.5 IP Adapter model to function correctly. It is compatible with version 3.2+ of Invoke AI. | |
| IP Adapter allows for users to input an Image Prompt, which is interpreted by the system, and passed in as conditioning for the image generation process. | |
| The Community Edition of Invoke AI can be found at invoke.ai or on GitHub at https://github.com/invoke-ai/InvokeAI | |
| Note: | |
| This model is a copy of https://huggingface.co/h94/IP-Adapter/tree/5c2eae7d8a9c3365ba4745f16b94eb0293e319d3/models/image_encoder. It is hosted here in a format compatibile with InvokeAI. | |