stabilityai / sd-vae-ft-mse-original

huggingface.co
Total runs: 5
24-hour runs: 0
7-day runs: 0
30-day runs: 4
Model's Last Updated: December 19 2022
text-to-image

Introduction of sd-vae-ft-mse-original

Model Details of sd-vae-ft-mse-original

Improved Autoencoders

Utilizing

These weights are intended to be used with the original CompVis Stable Diffusion codebase . If you are looking for the model to use with the 🧨 diffusers library, come here .

Decoder Finetuning

We publish two kl-f8 autoencoder versions, finetuned from the original kl-f8 autoencoder on a 1:1 ratio of LAION-Aesthetics and LAION-Humans, an unreleased subset containing only SFW images of humans. The intent was to fine-tune on the Stable Diffusion training set (the autoencoder was originally trained on OpenImages) but also enrich the dataset with images of humans to improve the reconstruction of faces. The first, ft-EMA , was resumed from the original checkpoint, trained for 313198 steps and uses EMA weights. It uses the same loss configuration as the original checkpoint (L1 + LPIPS). The second, ft-MSE , was resumed from ft-EMA and uses EMA weights and was trained for another 280k steps using a different loss, with more emphasis on MSE reconstruction (MSE + 0.1 * LPIPS). It produces somewhat ``smoother'' outputs. The batch size for both versions was 192 (16 A100s, batch size 12 per GPU). To keep compatibility with existing models, only the decoder part was finetuned; the checkpoints can be used as a drop-in replacement for the existing autoencoder..

Original kl-f8 VAE vs f8-ft-EMA vs f8-ft-MSE

Evaluation
COCO 2017 (256x256, val, 5000 images)
Model train steps rFID PSNR SSIM PSIM Link Comments
original 246803 4.99 23.4 +/- 3.8 0.69 +/- 0.14 1.01 +/- 0.28 https://ommer-lab.com/files/latent-diffusion/kl-f8.zip as used in SD
ft-EMA 560001 4.42 23.8 +/- 3.9 0.69 +/- 0.13 0.96 +/- 0.27 https://huggingface.co/stabilityai/sd-vae-ft-ema-original/resolve/main/vae-ft-ema-560000-ema-pruned.ckpt slightly better overall, with EMA
ft-MSE 840001 4.70 24.5 +/- 3.7 0.71 +/- 0.13 0.92 +/- 0.27 https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt resumed with EMA from ft-EMA, emphasis on MSE (rec. loss = MSE + 0.1 * LPIPS), smoother outputs
LAION-Aesthetics 5+ (256x256, subset, 10000 images)
Model train steps rFID PSNR SSIM PSIM Link Comments
original 246803 2.61 26.0 +/- 4.4 0.81 +/- 0.12 0.75 +/- 0.36 https://ommer-lab.com/files/latent-diffusion/kl-f8.zip as used in SD
ft-EMA 560001 1.77 26.7 +/- 4.8 0.82 +/- 0.12 0.67 +/- 0.34 https://huggingface.co/stabilityai/sd-vae-ft-ema-original/resolve/main/vae-ft-ema-560000-ema-pruned.ckpt slightly better overall, with EMA
ft-MSE 840001 1.88 27.3 +/- 4.7 0.83 +/- 0.11 0.65 +/- 0.34 https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt resumed with EMA from ft-EMA, emphasis on MSE (rec. loss = MSE + 0.1 * LPIPS), smoother outputs
Visual

Visualization of reconstructions on 256x256 images from the COCO2017 validation dataset.


256x256: ft-EMA (left), ft-MSE (middle), original (right)

Runs of stabilityai sd-vae-ft-mse-original on huggingface.co

5
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
4
30-day runs

More Information About sd-vae-ft-mse-original huggingface.co Model

More sd-vae-ft-mse-original license Visit here:

https://choosealicense.com/licenses/mit

sd-vae-ft-mse-original huggingface.co

sd-vae-ft-mse-original huggingface.co is an AI model on huggingface.co that provides sd-vae-ft-mse-original's model effect (), which can be used instantly with this stabilityai sd-vae-ft-mse-original model. huggingface.co supports a free trial of the sd-vae-ft-mse-original model, and also provides paid use of the sd-vae-ft-mse-original. Support call sd-vae-ft-mse-original model through api, including Node.js, Python, http.

sd-vae-ft-mse-original huggingface.co Url

https://huggingface.co/stabilityai/sd-vae-ft-mse-original

stabilityai sd-vae-ft-mse-original online free

sd-vae-ft-mse-original huggingface.co is an online trial and call api platform, which integrates sd-vae-ft-mse-original's modeling effects, including api services, and provides a free online trial of sd-vae-ft-mse-original, you can try sd-vae-ft-mse-original online for free by clicking the link below.

stabilityai sd-vae-ft-mse-original online free url in huggingface.co:

https://huggingface.co/stabilityai/sd-vae-ft-mse-original

sd-vae-ft-mse-original install

sd-vae-ft-mse-original is an open source model from GitHub that offers a free installation service, and any user can find sd-vae-ft-mse-original on GitHub to install. At the same time, huggingface.co provides the effect of sd-vae-ft-mse-original install, users can directly use sd-vae-ft-mse-original installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

sd-vae-ft-mse-original install url in huggingface.co:

https://huggingface.co/stabilityai/sd-vae-ft-mse-original

Url of sd-vae-ft-mse-original

sd-vae-ft-mse-original huggingface.co Url

Provider of sd-vae-ft-mse-original huggingface.co

stabilityai
ORGANIZATIONS

Other API from stabilityai

huggingface.co

Total runs: 143.2K
Run Growth: 8.3K
Growth Rate: 5.81%
Updated: August 04 2023
huggingface.co

Total runs: 137.2K
Run Growth: 16.4K
Growth Rate: 11.93%
Updated: July 10 2024
huggingface.co

Total runs: 34.3K
Run Growth: 3.4K
Growth Rate: 10.04%
Updated: August 09 2024
huggingface.co

Total runs: 378
Run Growth: -97.9K
Growth Rate: -25898.41%
Updated: August 03 2024
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated: July 10 2024
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated: April 14 2024