# Latent Diffusion Models [arXiv](https://arxiv.org/abs/2112.10752) | [BibTeX](#bibtex)

[**High-Resolution Image Synthesis with Latent Diffusion Models**](https://arxiv.org/abs/2112.10752)
[Robin Rombach](https://github.com/rromb)\*, [Andreas Blattmann](https://github.com/ablattmann)\*, [Dominik Lorenz](https://github.com/qp-qp)\, [Patrick Esser](https://github.com/pesser), [BjΓΆrn Ommer](https://hci.iwr.uni-heidelberg.de/Staff/bommer)
\* equal contribution

## News ### April 2022 - More pre-trained LDMs are available: - A 1.45B [model](#text-to-image) trained on the [LAION-400M](https://arxiv.org/abs/2111.02114) database. - A class-conditional model on ImageNet, achieving a FID of 3.6 when using [classifier-free guidance](https://openreview.net/pdf?id=qw8AKxfYbI) Available via a [colab notebook](https://colab.research.google.com/github/CompVis/latent-diffusion/blob/main/scripts/latent_imagenet_diffusion.ipynb) [![][colab]][colab-cin]. - Our 1.45B [latent diffusion LAION model](#text-to-image) was integrated into [Huggingface Spaces πŸ€—](https://huggingface.co/spaces) using [Gradio](https://github.com/gradio-app/gradio). Try out the Web Demo: [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/multimodalart/latentdiffusion) ## Requirements A suitable [conda](https://conda.io/) environment named `ldm` can be created and activated with: ``` conda env create -f environment.yaml conda activate ldm ``` # Pretrained Models A general list of all available checkpoints is available in via our [model zoo](#model-zoo). If you use any of these models in your work, we are always happy to receive a [citation](#bibtex). ## Text-to-Image ![text2img-figure](assets/txt2img-preview.png) Download the pre-trained weights (5.7GB) ``` mkdir -p models/ldm/text2img-large/ wget -O models/ldm/text2img-large/model.ckpt https://ommer-lab.com/files/latent-diffusion/nitro/txt2img-f8-large/model.ckpt ``` and sample with ``` python scripts/txt2img.py --prompt "a virus monster is playing guitar, oil on canvas" --ddim_eta 0.0 --n_samples 4 --n_iter 4 --scale 5.0 --ddim_steps 50 ``` This will save each sample individually as well as a grid of size `n_iter` x `n_samples` at the specified output location (default: `outputs/txt2img-samples`). Quality, sampling speed and diversity are best controlled via the `scale`, `ddim_steps` and `ddim_eta` arguments. As a rule of thumb, higher values of `scale` produce better samples at the cost of a reduced output diversity. Furthermore, increasing `ddim_steps` generally also gives higher quality samples, but returns are diminishing for values > 250. Fast sampling (i.e. low values of `ddim_steps`) while retaining good quality can be achieved by using `--ddim_eta 0.0`. Faster sampling (i.e. even lower values of `ddim_steps`) while retaining good quality can be achieved by using `--ddim_eta 0.0` and `--plms` (see [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://arxiv.org/abs/2202.09778)). #### Beyond 256Β² For certain inputs, simply running the model in a convolutional fashion on larger features than it was trained on can sometimes result in interesting results. To try it out, tune the `H` and `W` arguments (which will be integer-divided by 8 in order to calculate the corresponding latent size), e.g. run ``` python scripts/txt2img.py --prompt "a sunset behind a mountain range, vector image" --ddim_eta 1.0 --n_samples 1 --n_iter 1 --H 384 --W 1024 --scale 5.0 ``` to create a sample of size 384x1024. Note, however, that controllability is reduced compared to the 256x256 setting. The example below was generated using the above command. ![text2img-figure-conv](assets/txt2img-convsample.png) ## Inpainting ![inpainting](assets/inpainting.png) Download the pre-trained weights ``` wget -O models/ldm/inpainting_big/last.ckpt https://heibox.uni-heidelberg.de/f/4d9ac7ea40c64582b7c9/?dl=1 ``` and sample with ``` python scripts/inpaint.py --indir data/inpainting_examples/ --outdir outputs/inpainting_results ``` `indir` should contain images `*.png` and masks `_mask.png` like the examples provided in `data/inpainting_examples`. ## Class-Conditional ImageNet Available via a [notebook](scripts/latent_imagenet_diffusion.ipynb) [![][colab]][colab-cin]. ![class-conditional](assets/birdhouse.png) [colab]: [colab-cin]: ## Unconditional Models We also provide a script for sampling from unconditional LDMs (e.g. LSUN, FFHQ, ...). Start it via ```shell script CUDA_VISIBLE_DEVICES= python scripts/sample_diffusion.py -r models/ldm//model.ckpt -l -n <\#samples> --batch_size -c <\#ddim steps> -e <\#eta> ``` # Train your own LDMs ## Data preparation ### Faces For downloading the CelebA-HQ and FFHQ datasets, proceed as described in the [taming-transformers](https://github.com/CompVis/taming-transformers#celeba-hq) repository. ### LSUN The LSUN datasets can be conveniently downloaded via the script available [here](https://github.com/fyu/lsun). We performed a custom split into training and validation images, and provide the corresponding filenames at [https://ommer-lab.com/files/lsun.zip](https://ommer-lab.com/files/lsun.zip). After downloading, extract them to `./data/lsun`. The beds/cats/churches subsets should also be placed/symlinked at `./data/lsun/bedrooms`/`./data/lsun/cats`/`./data/lsun/churches`, respectively. ### ImageNet The code will try to download (through [Academic Torrents](http://academictorrents.com/)) and prepare ImageNet the first time it is used. However, since ImageNet is quite large, this requires a lot of disk space and time. If you already have ImageNet on your disk, you can speed things up by putting the data into `${XDG_CACHE}/autoencoders/data/ILSVRC2012_{split}/data/` (which defaults to `~/.cache/autoencoders/data/ILSVRC2012_{split}/data/`), where `{split}` is one of `train`/`validation`. It should have the following structure: ``` ${XDG_CACHE}/autoencoders/data/ILSVRC2012_{split}/data/ β”œβ”€β”€ n01440764 β”‚ β”œβ”€β”€ n01440764_10026.JPEG β”‚ β”œβ”€β”€ n01440764_10027.JPEG β”‚ β”œβ”€β”€ ... β”œβ”€β”€ n01443537 β”‚ β”œβ”€β”€ n01443537_10007.JPEG β”‚ β”œβ”€β”€ n01443537_10014.JPEG β”‚ β”œβ”€β”€ ... β”œβ”€β”€ ... ``` If you haven't extracted the data, you can also place `ILSVRC2012_img_train.tar`/`ILSVRC2012_img_val.tar` (or symlinks to them) into `${XDG_CACHE}/autoencoders/data/ILSVRC2012_train/` / `${XDG_CACHE}/autoencoders/data/ILSVRC2012_validation/`, which will then be extracted into above structure without downloading it again. Note that this will only happen if neither a folder `${XDG_CACHE}/autoencoders/data/ILSVRC2012_{split}/data/` nor a file `${XDG_CACHE}/autoencoders/data/ILSVRC2012_{split}/.ready` exist. Remove them if you want to force running the dataset preparation again. ## Model Training Logs and checkpoints for trained models are saved to `logs/_`. ### Training autoencoder models Configs for training a KL-regularized autoencoder on ImageNet are provided at `configs/autoencoder`. Training can be started by running ``` CUDA_VISIBLE_DEVICES= python main.py --base configs/autoencoder/.yaml -t --gpus 0, ``` where `config_spec` is one of {`autoencoder_kl_8x8x64`(f=32, d=64), `autoencoder_kl_16x16x16`(f=16, d=16), `autoencoder_kl_32x32x4`(f=8, d=4), `autoencoder_kl_64x64x3`(f=4, d=3)}. For training VQ-regularized models, see the [taming-transformers](https://github.com/CompVis/taming-transformers) repository. ### Training LDMs In ``configs/latent-diffusion/`` we provide configs for training LDMs on the LSUN-, CelebA-HQ, FFHQ and ImageNet datasets. Training can be started by running ```shell script CUDA_VISIBLE_DEVICES= python main.py --base configs/latent-diffusion/.yaml -t --gpus 0, ``` where ```` is one of {`celebahq-ldm-vq-4`(f=4, VQ-reg. autoencoder, spatial size 64x64x3),`ffhq-ldm-vq-4`(f=4, VQ-reg. autoencoder, spatial size 64x64x3), `lsun_bedrooms-ldm-vq-4`(f=4, VQ-reg. autoencoder, spatial size 64x64x3), `lsun_churches-ldm-vq-4`(f=8, KL-reg. autoencoder, spatial size 32x32x4),`cin-ldm-vq-8`(f=8, VQ-reg. autoencoder, spatial size 32x32x4)}. # Model Zoo ## Pretrained Autoencoding Models ![rec2](assets/reconstruction2.png) All models were trained until convergence (no further substantial improvement in rFID). | Model | rFID vs val | train steps |PSNR | PSIM | Link | Comments |-------------------------|------------|----------------|----------------|---------------|-------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------| | f=4, VQ (Z=8192, d=3) | 0.58 | 533066 | 27.43 +/- 4.26 | 0.53 +/- 0.21 | https://ommer-lab.com/files/latent-diffusion/vq-f4.zip | | | f=4, VQ (Z=8192, d=3) | 1.06 | 658131 | 25.21 +/- 4.17 | 0.72 +/- 0.26 | https://heibox.uni-heidelberg.de/f/9c6681f64bb94338a069/?dl=1 | no attention | | f=8, VQ (Z=16384, d=4) | 1.14 | 971043 | 23.07 +/- 3.99 | 1.17 +/- 0.36 | https://ommer-lab.com/files/latent-diffusion/vq-f8.zip | | | f=8, VQ (Z=256, d=4) | 1.49 | 1608649 | 22.35 +/- 3.81 | 1.26 +/- 0.37 | https://ommer-lab.com/files/latent-diffusion/vq-f8-n256.zip | | f=16, VQ (Z=16384, d=8) | 5.15 | 1101166 | 20.83 +/- 3.61 | 1.73 +/- 0.43 | https://heibox.uni-heidelberg.de/f/0e42b04e2e904890a9b6/?dl=1 | | | | | | | | | | | f=4, KL | 0.27 | 176991 | 27.53 +/- 4.54 | 0.55 +/- 0.24 | https://ommer-lab.com/files/latent-diffusion/kl-f4.zip | | | f=8, KL | 0.90 | 246803 | 24.19 +/- 4.19 | 1.02 +/- 0.35 | https://ommer-lab.com/files/latent-diffusion/kl-f8.zip | | | f=16, KL (d=16) | 0.87 | 442998 | 24.08 +/- 4.22 | 1.07 +/- 0.36 | https://ommer-lab.com/files/latent-diffusion/kl-f16.zip | | | f=32, KL (d=64) | 2.04 | 406763 | 22.27 +/- 3.93 | 1.41 +/- 0.40 | https://ommer-lab.com/files/latent-diffusion/kl-f32.zip | | ### Get the models Running the following script downloads und extracts all available pretrained autoencoding models. ```shell script bash scripts/download_first_stages.sh ``` The first stage models can then be found in `models/first_stage_models/` ## Pretrained LDMs | Datset | Task | Model | FID | IS | Prec | Recall | Link | Comments |---------------------------------|------|--------------|---------------|-----------------|------|------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------| | CelebA-HQ | Unconditional Image Synthesis | LDM-VQ-4 (200 DDIM steps, eta=0)| 5.11 (5.11) | 3.29 | 0.72 | 0.49 | https://ommer-lab.com/files/latent-diffusion/celeba.zip | | | FFHQ | Unconditional Image Synthesis | LDM-VQ-4 (200 DDIM steps, eta=1)| 4.98 (4.98) | 4.50 (4.50) | 0.73 | 0.50 | https://ommer-lab.com/files/latent-diffusion/ffhq.zip | | | LSUN-Churches | Unconditional Image Synthesis | LDM-KL-8 (400 DDIM steps, eta=0)| 4.02 (4.02) | 2.72 | 0.64 | 0.52 | https://ommer-lab.com/files/latent-diffusion/lsun_churches.zip | | | LSUN-Bedrooms | Unconditional Image Synthesis | LDM-VQ-4 (200 DDIM steps, eta=1)| 2.95 (3.0) | 2.22 (2.23)| 0.66 | 0.48 | https://ommer-lab.com/files/latent-diffusion/lsun_bedrooms.zip | | | ImageNet | Class-conditional Image Synthesis | LDM-VQ-8 (200 DDIM steps, eta=1) | 7.77(7.76)* /15.82** | 201.56(209.52)* /78.82** | 0.84* / 0.65** | 0.35* / 0.63** | https://ommer-lab.com/files/latent-diffusion/cin.zip | *: w/ guiding, classifier_scale 10 **: w/o guiding, scores in bracket calculated with script provided by [ADM](https://github.com/openai/guided-diffusion) | | Conceptual Captions | Text-conditional Image Synthesis | LDM-VQ-f4 (100 DDIM steps, eta=0) | 16.79 | 13.89 | N/A | N/A | https://ommer-lab.com/files/latent-diffusion/text2img.zip | finetuned from LAION | | OpenImages | Super-resolution | LDM-VQ-4 | N/A | N/A | N/A | N/A | https://ommer-lab.com/files/latent-diffusion/sr_bsr.zip | BSR image degradation | | OpenImages | Layout-to-Image Synthesis | LDM-VQ-4 (200 DDIM steps, eta=0) | 32.02 | 15.92 | N/A | N/A | https://ommer-lab.com/files/latent-diffusion/layout2img_model.zip | | | Landscapes | Semantic Image Synthesis | LDM-VQ-4 | N/A | N/A | N/A | N/A | https://ommer-lab.com/files/latent-diffusion/semantic_synthesis256.zip | | | Landscapes | Semantic Image Synthesis | LDM-VQ-4 | N/A | N/A | N/A | N/A | https://ommer-lab.com/files/latent-diffusion/semantic_synthesis.zip | finetuned on resolution 512x512 | ### Get the models The LDMs listed above can jointly be downloaded and extracted via ```shell script bash scripts/download_models.sh ``` The models can then be found in `models/ldm/`. ## Coming Soon... * More inference scripts for conditional LDMs. * In the meantime, you can play with our colab notebook https://colab.research.google.com/drive/1xqzUi2iXQXDqXBHQGP9Mqt2YrYW6cx-J?usp=sharing ## Comments - Our codebase for the diffusion models builds heavily on [OpenAI's ADM codebase](https://github.com/openai/guided-diffusion) and [https://github.com/lucidrains/denoising-diffusion-pytorch](https://github.com/lucidrains/denoising-diffusion-pytorch). Thanks for open-sourcing! - The implementation of the transformer encoder is from [x-transformers](https://github.com/lucidrains/x-transformers) by [lucidrains](https://github.com/lucidrains?tab=repositories). ## BibTeX ``` @misc{rombach2021highresolution, title={High-Resolution Image Synthesis with Latent Diffusion Models}, author={Robin Rombach and Andreas Blattmann and Dominik Lorenz and Patrick Esser and BjΓΆrn Ommer}, year={2021}, eprint={2112.10752}, archivePrefix={arXiv}, primaryClass={cs.CV} } ```