Skip to content

Commit

Permalink
update
Browse files Browse the repository at this point in the history
  • Loading branch information
@sangminwoo
sangminwoo committed May 29, 2024
1 parent 8f20104 commit 6ba3162
Show file tree
Hide file tree
Showing 2 changed files with 79 additions and 56 deletions.
135 changes: 79 additions & 56 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -174,16 +174,17 @@ <h2 class="title is-3">Abstract</h2>

<section class="hero is-small">
<div class="container">
<div class="hero-body">
<img src="static/images/main_table.png" alt="Main Table"/>
<h2 class="subtitle has-text-centered">
Patching the pre-trained DiT models with DMP.
We set two baselines for comparison:
(1) conventional fine-tuning to update the model parameters.
(2) naive prompt tuning.
Note that we use the same dataset as in the pre-training.
Image Resolution is 256 X 256.
</h2>
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-2">Diffusion Model Patching (DMP)</h2>
<div class="hero-body">
<img src="static/images/dmp.png" alt="Diffusion Model Patching"/>
<h2 class="subtitle has-text-centered">
DMP framework with DiT.
DMP reuses the original dataset used to pre-train DiT.
</h2>
</div>
</div>
</div>
</div>
</section>
Expand All @@ -192,12 +193,39 @@ <h2 class="subtitle has-text-centered">

<section class="hero is-small is-light">
<div class="container">
<div class="hero-body">
<img src="static/images/further_training.png" alt="Further Training"/>
<h2 class="subtitle has-text-centered">
(Left) Further training of fully converged DiT-L/2. DMP achieves a 10.38% gain in FID-50K with only 50K iterations, while others overfit.
(Right) Number of parameters. Default image size is 256x256.
</h2>
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-2">Results</h2>
<div class="hero-body">
<img src="static/images/main_table.png" alt="Main Table"/>
<h2 class="subtitle has-text-centered">
Patching the pre-trained DiT models with DMP.
We set two baselines for comparison:
(1) conventional fine-tuning to update the model parameters.
(2) naive prompt tuning.
Note that we use the same dataset as in the pre-training.
Image Resolution is 256 X 256.
</h2>
</div>
</div>
</div>
</div>
</section>



<section class="hero is-small">
<div class="container">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<div class="hero-body">
<img src="static/images/further_training.png" alt="Further Training"/>
<h2 class="subtitle has-text-centered">
(Left) Further training of fully converged DiT-L/2. DMP achieves a 10.38% gain in FID-50K with only 50K iterations, while others overfit.
(Right) Number of parameters. Default image size is 256x256.
</h2>
</div>
</div>
</div>
</div>
</section>
Expand All @@ -208,49 +236,44 @@ <h2 class="subtitle has-text-centered">
<section class="hero is-small">
<div class="hero-body">
<div class="container">
<div id="results-carousel" class="carousel results-carousel">
<div class="item">
<!-- Your image here -->
<div class="container">
<img src="static/images/output_image_golden_retriever.png" alt="Golden Retriever"/>
<h2 class="subtitle has-text-centered">
Uncurated 256×256 DiT-XL/2+DTR samples.
Classifier-free guidance scale = 1.5.
Class label = golden retriever (207)
</h2>
<div class="columns is-centered has-text-centered">
<h2 class="title is-2">ImageNet Results</h2>
<div id="results-carousel" class="carousel results-carousel">
<div class="item">
<!-- Your image here -->
<img src="static/images/output_image_golden_retriever.png" alt="Golden Retriever"/>
<h2 class="subtitle has-text-centered">
Uncurated 256×256 DiT-XL/2+DTR samples.
Classifier-free guidance scale = 1.5.
Class label = golden retriever (207)
</h2>
</div>
</div>
<div class="item">
<!-- Your image here -->
<div class="container">
<img src="static/images/output_image_goldfish.png" alt="Goldfish"/>
<h2 class="subtitle has-text-centered">
Uncurated 256×256 DiT-XL/2+DTR samples.
Classifier-free guidance scale = 1.5.
Class label = goldfish (1)
</h2>
<div class="item">
<!-- Your image here -->
<img src="static/images/output_image_goldfish.png" alt="Goldfish"/>
<h2 class="subtitle has-text-centered">
Uncurated 256×256 DiT-XL/2+DTR samples.
Classifier-free guidance scale = 1.5.
Class label = goldfish (1)
</h2>
</div>
</div>
<div class="item">
<!-- Your image here -->
<div class="container">
<img src="static/images/output_image_hummingbird.png" alt="Hummingbird"/>
<h2 class="subtitle has-text-centered">
Uncurated 256×256 DiT-XL/2+DTR samples.
Classifier-free guidance scale = 1.5.
Class label = hummingbird (94)
</h2>
<div class="item">
<!-- Your image here -->
<img src="static/images/output_image_hummingbird.png" alt="Hummingbird"/>
<h2 class="subtitle has-text-centered">
Uncurated 256×256 DiT-XL/2+DTR samples.
Classifier-free guidance scale = 1.5.
Class label = hummingbird (94)
</h2>
</div>
</div>
<div class="item">
<!-- Your image here -->
<div class="container">
<img src="static/images/output_image_ostrich.png" alt="Ostrich"/>
<h2 class="subtitle has-text-centered">
Uncurated 256×256 DiT-XL/2+DTR samples.
Classifier-free guidance scale = 1.5.
Class label = “ostrich” (9)
</h2>
<div class="item">
<!-- Your image here -->
<img src="static/images/output_image_ostrich.png" alt="Ostrich"/>
<h2 class="subtitle has-text-centered">
Uncurated 256×256 DiT-XL/2+DTR samples.
Classifier-free guidance scale = 1.5.
Class label = “ostrich” (9)
</h2>
</div>
</div>
</div>
Expand Down
Binary file added static/images/dmp.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit 6ba3162

Please sign in to comment.