Skip to content

Commit

Permalink
links
Browse files Browse the repository at this point in the history
  • Loading branch information
@vpj
vpj committed Sep 15, 2022
1 parent 5d4f383 commit 4c47086
Show file tree
Hide file tree
Showing 8 changed files with 94 additions and 80 deletions.
2 changes: 1 addition & 1 deletion docs/diffusion/stable_diffusion/latent_diffusion.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@
<a href='#section-0'>#</a>
</div>
<h1>Latent Diffusion Models</h1>
<p>Latent diffusion models use an auto-encoder to map between image space and latent space. The diffusion model works on the diffusion space, which makes it a lot easier to train. It is based on paper <a href="https://arxiv.org/abs/2112.10752">High-Resolution Image Synthesis with Latent Diffusion Models</a>.</p>
<p>Latent diffusion models use an auto-encoder to map between image space and latent space. The diffusion model works on the diffusion space, which makes it a lot easier to train. It is based on paper <a href="https://papers.labml.ai/paper/2112.10752">High-Resolution Image Synthesis with Latent Diffusion Models</a>.</p>
<p>They use a pre-trained auto-encoder and train the diffusion U-Net on the latent space of the pre-trained auto-encoder.</p>
<p>For a simpler diffusion implementation refer to our <a href="../ddpm/index.html">DDPM implementation</a>. We use same notations for <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqd" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-left:-0.0037em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqj" style="">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span></span>, <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqe" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqf" style="margin-right:0.05278em">β</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqj" style="">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span></span> schedules, etc.</p>

Expand Down
37 changes: 20 additions & 17 deletions docs/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -101,32 +101,39 @@ <h4>✨ <a href="transformers/index.html">Transformers</a></h4>
<li><a href="transformers/vit/index.html">Vision Transformer (ViT)</a> </li>
<li><a href="transformers/primer_ez/index.html">Primer EZ</a> </li>
<li><a href="transformers/hour_glass/index.html">Hourglass</a></li></ul>
<h4>✨ <a href="recurrent_highway_networks/index.html">Recurrent Highway Networks</a></h4>
<h4>✨ <a href="lstm/index.html">LSTM</a></h4>
<h4>✨ <a href="hypernetworks/hyper_lstm.html">HyperNetworks - HyperLSTM</a></h4>
<h4>✨ <a href="resnet/index.html">ResNet</a></h4>
<h4>✨ <a href="conv_mixer/index.html">ConvMixer</a></h4>
<h4>✨ <a href="capsule_networks/index.html">Capsule Networks</a></h4>
<h4>✨ <a href="unet/index.html">U-Net</a></h4>
<h4>✨ <a href="neox/index.html">Eleuther GPT-NeoX</a></h4>
<ul><li><a href="neox/samples/generate.html">Generate on a 48GB GPU</a> </li>
<li><a href="neox/samples/finetune.html">Finetune on two 48GB GPUs</a> </li>
<li><a href="neox/utils/llm_int8.html">LLM.int8()</a></li></ul>
<h4>✨ <a href="diffusion/index.html">Diffusion models</a></h4>
<ul><li><a href="diffusion/ddpm/index.html">Denoising Diffusion Probabilistic Models (DDPM)</a> </li>
<li><a href="diffusion/stable_diffusion/sampler/ddim.html">Denoising Diffusion Implicit Models (DDIM)</a> </li>
<li><a href="diffusion/stable_diffusion/latent_diffusion.html">Latent Diffusion Models</a> </li>
<li><a href="diffusion/stable_diffusion/index.html">Stable Diffusion</a></li></ul>
<h4>✨ <a href="gan/index.html">Generative Adversarial Networks</a></h4>
<ul><li><a href="gan/original/index.html">Original GAN</a> </li>
<li><a href="gan/dcgan/index.html">GAN with deep convolutional network</a> </li>
<li><a href="gan/cycle_gan/index.html">Cycle GAN</a> </li>
<li><a href="gan/wasserstein/index.html">Wasserstein GAN</a> </li>
<li><a href="gan/wasserstein/gradient_penalty/index.html">Wasserstein GAN with Gradient Penalty</a> </li>
<li><a href="gan/stylegan/index.html">StyleGAN 2</a></li></ul>
<h4>✨ <a href="diffusion/index.html">Diffusion models</a></h4>
<ul><li><a href="diffusion/ddpm/index.html">Denoising Diffusion Probabilistic Models (DDPM)</a></li></ul>
<h4>✨ <a href="recurrent_highway_networks/index.html">Recurrent Highway Networks</a></h4>
<h4>✨ <a href="lstm/index.html">LSTM</a></h4>
<h4>✨ <a href="hypernetworks/hyper_lstm.html">HyperNetworks - HyperLSTM</a></h4>
<h4>✨ <a href="resnet/index.html">ResNet</a></h4>
<h4>✨ <a href="conv_mixer/index.html">ConvMixer</a></h4>
<h4>✨ <a href="capsule_networks/index.html">Capsule Networks</a></h4>
<h4>✨ <a href="unet/index.html">U-Net</a></h4>
<h4>✨ <a href="sketch_rnn/index.html">Sketch RNN</a></h4>
<h4>✨ Graph Neural Networks</h4>
<ul><li><a href="graphs/gat/index.html">Graph Attention Networks (GAT)</a> </li>
<li><a href="graphs/gatv2/index.html">Graph Attention Networks v2 (GATv2)</a></li></ul>
<h4>✨ <a href="cfr/index.html">Counterfactual Regret Minimization (CFR)</a></h4>
<p>Solving games with incomplete information such as poker with CFR.</p>
<ul><li><a href="cfr/kuhn/index.html">Kuhn Poker</a></li></ul>
<h4>✨ <a href="rl/index.html">Reinforcement Learning</a></h4>
<ul><li><a href="rl/ppo/index.html">Proximal Policy Optimization</a> with <a href="rl/ppo/gae.html">Generalized Advantage Estimation</a> </li>
<li><a href="rl/dqn/index.html">Deep Q Networks</a> with with <a href="rl/dqn/model.html">Dueling Network</a>, <a href="rl/dqn/replay_buffer.html">Prioritized Replay</a> and Double Q Network.</li></ul>
<h4>✨ <a href="cfr/index.html">Counterfactual Regret Minimization (CFR)</a></h4>
<p>Solving games with incomplete information such as poker with CFR.</p>
<ul><li><a href="cfr/kuhn/index.html">Kuhn Poker</a></li></ul>
<h4>✨ <a href="optimizers/index.html">Optimizers</a></h4>
<ul><li><a href="optimizers/adam.html">Adam</a> </li>
<li><a href="optimizers/amsgrad.html">AMSGrad</a> </li>
Expand All @@ -149,15 +156,11 @@ <h4>✨ <a href="uncertainty/index.html">Uncertainty</a></h4>
<ul><li><a href="uncertainty/evidence/index.html">Evidential Deep Learning to Quantify Classification Uncertainty</a></li></ul>
<h4>✨ <a href="activations/index.html">Activations</a></h4>
<ul><li><a href="activations/fta/index.html">Fuzzy Tiling Activations</a></li></ul>
<h4>✨ <a href="sampling/index.html">Sampling Techniques</a></h4>
<h4>✨ <a href="sampling/index.html">Language Model Sampling Techniques</a></h4>
<ul><li><a href="sampling/greedy.html">Greedy Sampling</a> </li>
<li><a href="sampling/temperature.html">Temperature Sampling</a> </li>
<li><a href="sampling/top_k.html">Top-k Sampling</a> </li>
<li><a href="sampling/nucleus.html">Nucleus Sampling</a></li></ul>
<h4>✨ <a href="neox/index.html">Eleuther GPT-NeoX</a></h4>
<ul><li><a href="neox/samples/generate.html">Generate on a 48GB GPU</a> </li>
<li><a href="neox/samples/finetune.html">Finetune on two 48GB GPUs</a> </li>
<li><a href="neox/utils/llm_int8.html">LLM.int8()</a></li></ul>
<h4>✨ <a href="scaling/index.html">Scalable Training/Inference</a></h4>
<ul><li><a href="scaling/zero3/index.html">Zero3 memory optimizations</a></li></ul>
<h2>Highlighted Research Paper PDFs</h2>
Expand Down
6 changes: 6 additions & 0 deletions docs/papers.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -123,6 +123,9 @@
"2006.11239": [
"https://nn.labml.ai/diffusion/ddpm/index.html"
],
"2010.02502": [
"https://nn.labml.ai/diffusion/stable_diffusion/sampler/ddim.html"
],
"2010.07468": [
"https://nn.labml.ai/optimizers/ada_belief.html"
],
Expand Down Expand Up @@ -168,6 +171,9 @@
"2112.04426": [
"https://nn.labml.ai/transformers/retro/index.html"
],
"2112.10752": [
"https://nn.labml.ai/diffusion/stable_diffusion/latent_diffusion.html"
],
"2201.09792": [
"https://nn.labml.ai/conv_mixer/index.html"
],
Expand Down
34 changes: 17 additions & 17 deletions docs/sitemap.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -134,7 +134,7 @@

<url>
<loc>https://nn.labml.ai/neox/checkpoint.html</loc>
<lastmod>2022-08-11T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>

Expand Down Expand Up @@ -533,112 +533,112 @@

<url>
<loc>https://nn.labml.ai/diffusion/index.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/util.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/index.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/latent_diffusion.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/sampler/ddim.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/sampler/index.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/sampler/ddpm.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/scripts/text_to_image.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/scripts/in_paint.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/scripts/index.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/scripts/image_to_image.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/model/unet.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/model/index.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/model/clip_embedder.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/model/autoencoder.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>


<url>
<loc>https://nn.labml.ai/diffusion/stable_diffusion/model/unet_attention.html</loc>
<lastmod>2022-09-12T16:30:00+00:00</lastmod>
<lastmod>2022-09-15T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>

Expand Down
51 changes: 27 additions & 24 deletions labml_nn/__init__.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,26 @@
* [Primer EZ](transformers/primer_ez/index.html)
* [Hourglass](transformers/hour_glass/index.html)
#### ✨ [Eleuther GPT-NeoX](neox/index.html)
* [Generate on a 48GB GPU](neox/samples/generate.html)
* [Finetune on two 48GB GPUs](neox/samples/finetune.html)
* [LLM.int8()](neox/utils/llm_int8.html)
#### ✨ [Diffusion models](diffusion/index.html)
* [Denoising Diffusion Probabilistic Models (DDPM)](diffusion/ddpm/index.html)
* [Denoising Diffusion Implicit Models (DDIM)](diffusion/stable_diffusion/sampler/ddim.html)
* [Latent Diffusion Models](diffusion/stable_diffusion/latent_diffusion.html)
* [Stable Diffusion](diffusion/stable_diffusion/index.html)
#### ✨ [Generative Adversarial Networks](gan/index.html)
* [Original GAN](gan/original/index.html)
* [GAN with deep convolutional network](gan/dcgan/index.html)
* [Cycle GAN](gan/cycle_gan/index.html)
* [Wasserstein GAN](gan/wasserstein/index.html)
* [Wasserstein GAN with Gradient Penalty](gan/wasserstein/gradient_penalty/index.html)
* [StyleGAN 2](gan/stylegan/index.html)
#### ✨ [Recurrent Highway Networks](recurrent_highway_networks/index.html)
#### ✨ [LSTM](lstm/index.html)
Expand All @@ -55,31 +75,13 @@
#### ✨ [U-Net](unet/index.html)
#### ✨ [Generative Adversarial Networks](gan/index.html)
* [Original GAN](gan/original/index.html)
* [GAN with deep convolutional network](gan/dcgan/index.html)
* [Cycle GAN](gan/cycle_gan/index.html)
* [Wasserstein GAN](gan/wasserstein/index.html)
* [Wasserstein GAN with Gradient Penalty](gan/wasserstein/gradient_penalty/index.html)
* [StyleGAN 2](gan/stylegan/index.html)
#### ✨ [Diffusion models](diffusion/index.html)
* [Denoising Diffusion Probabilistic Models (DDPM)](diffusion/ddpm/index.html)
#### ✨ [Sketch RNN](sketch_rnn/index.html)
#### ✨ Graph Neural Networks
* [Graph Attention Networks (GAT)](graphs/gat/index.html)
* [Graph Attention Networks v2 (GATv2)](graphs/gatv2/index.html)
#### ✨ [Counterfactual Regret Minimization (CFR)](cfr/index.html)
Solving games with incomplete information such as poker with CFR.
* [Kuhn Poker](cfr/kuhn/index.html)
#### ✨ [Reinforcement Learning](rl/index.html)
* [Proximal Policy Optimization](rl/ppo/index.html) with
[Generalized Advantage Estimation](rl/ppo/gae.html)
Expand All @@ -88,6 +90,12 @@
[Prioritized Replay](rl/dqn/replay_buffer.html)
and Double Q Network.
#### ✨ [Counterfactual Regret Minimization (CFR)](cfr/index.html)
Solving games with incomplete information such as poker with CFR.
* [Kuhn Poker](cfr/kuhn/index.html)
#### ✨ [Optimizers](optimizers/index.html)
* [Adam](optimizers/adam.html)
* [AMSGrad](optimizers/amsgrad.html)
Expand Down Expand Up @@ -119,17 +127,12 @@
* [Fuzzy Tiling Activations](activations/fta/index.html)
#### ✨ [Sampling Techniques](sampling/index.html)
#### ✨ [Language Model Sampling Techniques](sampling/index.html)
* [Greedy Sampling](sampling/greedy.html)
* [Temperature Sampling](sampling/temperature.html)
* [Top-k Sampling](sampling/top_k.html)
* [Nucleus Sampling](sampling/nucleus.html)
#### ✨ [Eleuther GPT-NeoX](neox/index.html)
* [Generate on a 48GB GPU](neox/samples/generate.html)
* [Finetune on two 48GB GPUs](neox/samples/finetune.html)
* [LLM.int8()](neox/utils/llm_int8.html)
#### ✨ [Scalable Training/Inference](scaling/index.html)
* [Zero3 memory optimizations](scaling/zero3/index.html)
Expand Down
2 changes: 1 addition & 1 deletion labml_nn/diffusion/stable_diffusion/latent_diffusion.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
latent space. The diffusion model works on the diffusion space, which makes it
a lot easier to train.
It is based on paper
[High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752).
[High-Resolution Image Synthesis with Latent Diffusion Models](https://papers.labml.ai/paper/2112.10752).
They use a pre-trained auto-encoder and train the diffusion U-Net on the latent
space of the pre-trained auto-encoder.
Expand Down
Loading

0 comments on commit 4c47086

Please sign in to comment.