You can integrate this fine-tuned VAE decoder to your existing
diffusers
workflows, by including a
vae
argument to the
StableDiffusionPipeline
from diffusers.models import AutoencoderKL
from diffusers import StableDiffusionPipeline
model = "stabilityai/your-stable-diffusion-model"
vae = AutoencoderKL.from_pretrained("stabilityai/sdxl-vae")
pipe = StableDiffusionPipeline.from_pretrained(model, vae=vae)
Model
SDXL
is a
latent diffusion model
, where the diffusion operates in a pretrained,
learned (and fixed) latent space of an autoencoder.
While the bulk of the semantic composition is done by the latent diffusion model,
we can improve
local
, high-frequency details in generated images by improving the quality of the autoencoder.
To this end, we train the same autoencoder architecture used for the original
Stable Diffusion
at a larger batch-size (256 vs 9)
and additionally track the weights with an exponential moving average (EMA).
The resulting autoencoder outperforms the original model in all evaluated reconstruction metrics, see the table below.
sdxl-vae huggingface.co is an AI model on huggingface.co that provides sdxl-vae's model effect (), which can be used instantly with this stabilityai sdxl-vae model. huggingface.co supports a free trial of the sdxl-vae model, and also provides paid use of the sdxl-vae. Support call sdxl-vae model through api, including Node.js, Python, http.
sdxl-vae huggingface.co is an online trial and call api platform, which integrates sdxl-vae's modeling effects, including api services, and provides a free online trial of sdxl-vae, you can try sdxl-vae online for free by clicking the link below.
stabilityai sdxl-vae online free url in huggingface.co:
sdxl-vae is an open source model from GitHub that offers a free installation service, and any user can find sdxl-vae on GitHub to install. At the same time, huggingface.co provides the effect of sdxl-vae install, users can directly use sdxl-vae installed effect in huggingface.co for debugging and trial. It also supports api for free installation.