mlpc-lab/TokenCompose_SD14_A
🧩 TokenCompose SD14 Model Card
🎬CVPR 2024
TokenCompose_SD14_A is a latent text-to-image diffusion model finetuned from the **Stable-Diffusion-v1-4** checkpoint at resolution 512x512 on the VSR split of COCO image-caption pairs for 24,000 steps with a learning rate of 5e-6. The training objective involves token-level grounding terms in addition to denoising loss for enhanced multi-category instance composition and photorealism. The "_A/B" postfix indicates different finetuning runs of the model using the same above configurations.
📄 Paper
Please follow this link.
🧨Example Usage
We strongly recommend using the 🤗Diffuser library to run our model.
import torch
from diffusers import StableDiffusionPipeline
model_id = "mlpc-lab/TokenCompose_SD14_A"
device = "cuda"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float32)
pipe = pipe.to(device)
prompt = "A cat and a wine glass"
image = pipe(prompt).images[0]
image.save("cat_and_wine_glass.png")⬆️Improvements over SD14
<table>
<tr> <th rowspan="3" align="center">Method</th> <th colspan="9" align="center">Multi-category Instance Composition</th> <th colspan="2" align="center">Photorealism</th> <th colspan="1" align="center">Efficiency</th> </tr>
<tr> <!-- <th align="center"> </th> --> <th rowspan="2" align="center">Object Accuracy</th> <th colspan="4" align="center">COCO</th> <th colspan="4" align="center">ADE20K</th> <th rowspan="2" align="center">FID (COCO)</th> <th rowspan="2" align="center">FID (Flickr30K)</th> <th rowspan="2" align="center">Latency</th> </tr>
<tr> <!-- <th align="center"> </th> --> <th align="center">MG2</th> <th align="center">MG3</th> <th align="center">MG4</th> <th align="center">MG5</th> <th align="center">MG2</th> <th align="center">MG3</th> <th align="center">MG4</th> <th align="center">MG5</th> </tr>
<tr> <td align="center"><a href="https://huggingface.co/CompVis/stable-diffusion-v1-4">SD 1.4</a></td> <td align="center">29.86</td> <td align="center">90.72<sub>1.33</sub></td> <td align="center">50.74<sub>0.89</sub></td> <td align="center">11.68<sub>0.45</sub></td> <td align="center">0.88<sub>0.21</sub></td> <td align="center">89.81<sub>0.40</sub></td> <td align="center">53.96<sub>1.14</sub></td> <td align="center">16.52<sub>1.13</sub></td> <td align="center">1.89<sub>0.34</sub></td> <td align="center"><u>20.88</u></td> <td align="center"><u>71.46</u></td> <td align="center"><b>7.54</b><sub>0.17</sub></td> </tr>
<tr> <td align="center"><a href="https://github.com/mlpc-ucsd/TokenCompose"><strong>TokenCompose (Ours)</strong></a></td> <td align="center"><b>52.15</b></td> <td align="center"><b>98.08</b><sub>0.40</sub></td> <td align="center"><b>76.16</b><sub>1.04</sub></td> <td align="center"><b>28.81</b><sub>0.95</sub></td> <td align="center"><u>3.28</u><sub>0.48</sub></td> <td align="center"><b>97.75</b><sub>0.34</sub></td> <td align="center"><b>76.93</b><sub>1.09</sub></td> <td align="center"><b>33.92</b><sub>1.47</sub></td> <td align="center"><b>6.21</b><sub>0.62</sub></td> <td align="center"><b>20.19</b></td> <td align="center"><b>71.13</b></td> <td align="center"><b>7.56</b><sub>0.14</sub></td> </tr>
</table>
📰 Citation
@InProceedings{Wang2024TokenCompose,
author = {Wang, Zirui and Sha, Zhizhou and Ding, Zheng and Wang, Yilin and Tu, Zhuowen},
title = {TokenCompose: Text-to-Image Diffusion with Token-level Supervision},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2024},
pages = {8553-8564}
}