1580158
/
IP-Adapter
mirror of https://github.com/tencent-ailab/IP-Adapter
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update README.md

pull/32/head
Hu Ye 2023-09-01 20:19:52 +08:00 committed by GitHub
parent ad0bcf4f42
commit 5ac5c2b9f8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
README.md
View File

@ -10,16 +10,7 @@
## Introduction
we present IP-Adapter, an effective and lightweight
adapter to achieve image prompt capability for the pre-trained
text-to-image diffusion models. An IP-Adapter
with only 22M parameters can achieve comparable or even
better performance to a fine-tuned image prompt model. IP-Adapter
can be generalized not only to other custom models
fine-tuned from the same base model, but also to controllable
generation using existing controllable tools. Moreover, the image prompt
can also work well with the text prompt to accomplish multimodal
image generation.
we present IP-Adapter, an effective and lightweight adapter to achieve image prompt capability for the pre-trained text-to-image diffusion models. An IP-Adapter with only 22M parameters can achieve comparable or even better performance to a fine-tuned image prompt model. IP-Adapter can be generalized not only to other custom models fine-tuned from the same base model, but also to controllable generation using existing controllable tools. Moreover, the image prompt can also work well with the text prompt to accomplish multimodal image generation.
![arch](assets/figs/fig1.png)
@ -98,7 +89,7 @@ accelerate launch --num_processes 8 --multi_gpu --mixed_precision "fp16" \
## Disclaimer
This project strives to positively impact the domain of AI-driven image generation. Users are granted the freedom to create images using this tool, but they are expected to comply with local laws and employ the software responsibly. **The developers do not assume any responsibility for potential misuse by users.**
This project strives to positively impact the domain of AI-driven image generation. Users are granted the freedom to create images using this tool, but they are expected to comply with local laws and utilize it in a responsible manner. **The developers do not assume any responsibility for potential misuse by users.**
## Citation
If you find IP-Adapter useful for your research and applications, please cite using this BibTeX: