ModelListedExternal

BiliSakura/VAEs · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Sourcehuggingface.co/BiliSakura/VAEs

KindOtherBgrade

Model source

Kind: Other
File size: 122 MB–1.22 GB
Updated: Sep 19, 2026
Source: Hugging Face

Source excerpt

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Sources

1 source

Hugging FaceSource

huggingface.co/BiliSakura/VAEs

Verified Sep 15

Download files

Model artifacts

12 artifacts

IBQ-VQVAE-1024/diffusion_pytorch_model.safetensors

safetensors · 408 MB · SHA-256 57a7dfdee26e…5a75

IBQ-VQVAE-16384/diffusion_pytorch_model.safetensors

safetensors · 423 MB · SHA-256 772f0f3f3518…ec6c

IBQ-VQVAE-262144/diffusion_pytorch_model.safetensors

safetensors · 663 MB · SHA-256 b37947699d08…5843

IBQ-VQVAE-8192/diffusion_pytorch_model.safetensors

safetensors · 415 MB · SHA-256 e4726ed0f916…f9bc

MOVQGAN-102M/diffusion_pytorch_model.safetensors

safetensors · 388 MB · SHA-256 70223deeafa2…3e3d

MOVQGAN-270M/diffusion_pytorch_model.safetensors

safetensors · 1.01 GB · SHA-256 e8b346d58445…e161

MOVQGAN-67M/diffusion_pytorch_model.safetensors

safetensors · 259 MB · SHA-256 43a5860fea19…7002

SANA-VAE/diffusion_pytorch_model.safetensors

safetensors · 1.16 GB · SHA-256 15a4b09e56d9…d87f

SD-CD-VAE/diffusion_pytorch_model.safetensors

safetensors · 1.22 GB · SHA-256 df6386a06f74…1cfb

SD21-VAE/diffusion_pytorch_model.safetensors

safetensors · FP16 (tensor header) · 160 MB · SHA-256 3e4c08995484…af9a

SDXL-VAE/diffusion_pytorch_model.safetensors

safetensors · 160 MB · SHA-256 bcb60880a46b…1e68

VQDIFFUSION-VQVAE/diffusion_pytorch_model.safetensors

safetensors · 122 MB · SHA-256 a51e9ecabf08…a20c

Source excerpts

2 excerpts

ReadmeJul 31huggingface.co/BiliSakura/VAEs

--- license: apache-2.0 tags: - vae - autoencoder - image - stable-diffusion - sdxl - flux - sana - qwen pipeline_tag: image-to-image library_name: diffusers language: - en --- # VAEs for Image Generation This repository hosts a curated collection of VAE checkpoints used by diffusion and transformer-based image generation pipelines. ## Available VAEs ### AutoencoderKL | Model | Source | Latent Channels | |-------|--------|-----------------| | SD21-VAE | Stable Diffusion 2.1 | 4 | | SDXL-VAE | Stable Diffusion XL | 4 | | SD35-VAE | Stable Diffusion 3.5 | 16 | | FLUX1-VAE | FLUX.1 | 16 | | FLUX2-VAE | FLUX.2 | 32 | | SANA-VAE | SANA (DC-AE) | 32 | | Qwen-VAE | Qwen-Image | 16 | ### VQModel | Model | Source | latent_channels | num_vq_embeddings | vq_embed_dim | sample_size | |-------|--------|-----------------|-------------------|--------------|-------------| | VQDIFFUSION-VQVAE | VQ-Diffusion (microsoft/vq-diffusion-ithq) | 256 | 4096 | 128 | 32 | | IBQ-VQVAE-1024 | IBQ (TencentARC/SEED) | 256 | 1024 | 256 | 32 | | IBQ-VQVAE-8192 | IBQ (TencentARC/SEED) | 256 | 8192 | 256 | 32 | | IBQ-VQVAE-16384 | IBQ (TencentARC/SEED) | 256 | 16384 | 256 | 32 | | IBQ-VQVAE-262144 | IBQ (TencentARC/SEED) | 256 | 262144 | 256 | 32 | | MOVQGAN-67M | MOVQGAN | 4 | 16384 | 4 | 256 | | MOVQGAN-102M | MOVQGAN | 4 | 16384 | 4 | 256 | | MOVQGAN-270M | MOVQGAN | 4 | 16384 | 4 | 256 | ## Diffusers usage **AutoencoderKL** (SD, FLUX, SANA, Qwen, etc.): ```python from diffusers import AutoencoderKL vae = AutoencoderKL.from_pretrained( "BiliSakura/VAEs", subfolder="SDXL-VAE", ) ``` **VQModel** (VQ-Diffusion, IBQ, MOVQGAN): ```python from diffusers import VQModel vae = VQModel.from_pretrained( "BiliSakura/VAEs", subfolder="VQDIFFUSION-VQVAE", ) ``` ## Notes - All models are VAE checkpoints intended for inference use in their corresponding pipelines. - Latent channel count is listed to help match with the correct backbone.

NoteJul 31huggingface.co/BiliSakura/VAEs

Source context: 0 downloads · 0 likes · Pipeline image-to-image · Library diffusers · Repo BiliSakura/VAEs