CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.image / sd-vae-ft-ema-original
From: stabilityai <huggingface.co/stabilityai>Newsgroups: alt.freeweights.imageSubject:

sd-vae-ft-ema-original

Date: 2026-11-14Commit: e21db4dSigned: 2DC28CC7B26A283B ✓

Text to image model. Safetensors weights, 676 MB in all. Published by stabilityai under MIT.

image676MBsd-vae-ft-ema-originalsafetensorspermissive
FactsParamsnot statedSize676 MBFormatssafetensorsTasktext to imageLicenseMITFrom sourcepermissive
$ fw get stabilityai/sd-vae-ft-ema-original
# manifest sha256 6cab4215bbaa… · 676 MB · 36 files
$ fw verify ./sd-vae-ft-ema-original stabilityai/sd-vae-ft-ema-original
From sourceHosted (signed)stabilityai/sd-vae-ft-ema-originalLast check: 2026-11-15 02:25 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Works with

Run16Fine-tune8Convert8Scan2
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
676 MB
Weights
335 MB (safetensors)
Parameters
not stated
Formats
safetensors
Task
text to image
License
MIT (permissive)
Files
36, each with a sha256
Publisher
stabilityai
Added
2026-11-14
Section
alt.freeweights.image
Lineage

Original release from the publisher.

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 02:25 UTCpassed

Model card

From the publisher at commit e21db4d. Shown as plain text with links; images open at the publisher.

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)

Image: image

Image: image

Image: image

Image: image

Image: image

Image: image

Files

36 files · 676 MBWeights 335 MB (safetensors). Sizes and sha256 from the signed manifest.
Show all 36 files with their sha256
FileSizesha256
.gitattributes1.67 KB82a09fe1027a6c5852922404641316b42189dae1d992981115c0d503b60670b1
README.md6.36 KB1a0f4be40a269cd8c3122599a1215da498f1dab5c6c7e90df3437c12b7dfe330
eval/ae-decoder-tuning-reconstructions/ft-ema/00011.png132 KB96c23fee5234bd99f7af4729ea774dea6452167a3dc568a132bf4c0eb3b60f33
eval/ae-decoder-tuning-reconstructions/ft-ema/00025.png114 KBfee5f09828a9ce6a3938c3ed3bc0751525b41e2dc5e988073a593686d6f82eb1
eval/ae-decoder-tuning-reconstructions/ft-ema/00029.png106 KBd3f449adf75fb85c4a4fef7fc8bef122851316cda8cac7163792ac97c43eb105
eval/ae-decoder-tuning-reconstructions/ft-ema/00037.png120 KBca4803079b102fe68b7a9e63b3742dcca9c2efdae54d180fe1c1b19ce49b772b
eval/ae-decoder-tuning-reconstructions/ft-ema/00043.png69.4 KB20ab646fa1bb1192959314b8ef0a2c687c52591cef92a0c7293f226d8b703bc5
eval/ae-decoder-tuning-reconstructions/ft-ema/00051.png134 KB848394ee0c4e7594293aeaa1af099d969eaf1e8fab7defd4875f5ea65b2f2bdc
eval/ae-decoder-tuning-reconstructions/ft-ema/00053.png161 KB70b8909690a169a8e1db2c79cdacfd6afa8899cb5b84fa4f89b02bbf40f161ab
eval/ae-decoder-tuning-reconstructions/ft-ema/00055.png146 KB0cfc8ceb7f088a33f3b26099936097da9dd34e508ae3e58bec4a34c88426e621
eval/ae-decoder-tuning-reconstructions/ft-mse/00011.png126 KB75e34649477bbaa406b0bb3cabcb7c6dd662a0b84b1247bba3fc8d7d9ab02546
eval/ae-decoder-tuning-reconstructions/ft-mse/00025.png115 KB5c33b3824f947d20da17f037a29058f442d16db66c2bbc9376ca879e5638495c
eval/ae-decoder-tuning-reconstructions/ft-mse/00029.png105 KB9a7832e908962901d70b6020bdc369f56865118344c4934771bbdb32ff44c0fb
eval/ae-decoder-tuning-reconstructions/ft-mse/00037.png115 KBd66c734768fd36c868763a23dda98a39d7a42b66b424ef5849bcd87ec25feea6
eval/ae-decoder-tuning-reconstructions/ft-mse/00043.png70.7 KBcff525f15e9df840c2371114da31f51e3c6bf99df78b09646ea9684158ed5bac
eval/ae-decoder-tuning-reconstructions/ft-mse/00051.png126 KB55c5ffa8e239462d74a3c9ad93e8b10f1c04820d0aaecb46e25306737624ed66
eval/ae-decoder-tuning-reconstructions/ft-mse/00053.png149 KB7dc1d8407593367ad1cec88721af138a2c7ae8059f4d96f619cbf8d845377c6d
eval/ae-decoder-tuning-reconstructions/ft-mse/00055.png137 KB5dc1a9fae6026d160749c88cf7fc08ec23d3d5355067354067dea5feebb3cacc
eval/ae-decoder-tuning-reconstructions/merged/00011_merged.png446 KB84370dcadb17931c32fc9c839c59adb34120be81b99ea9aed603c7073025afbe
eval/ae-decoder-tuning-reconstructions/merged/00025_merged.png387 KB9cf7db2493c8f56c8edfe4ff93a463d6e09d28bd17d0b9ae465ad393013d4168
eval/ae-decoder-tuning-reconstructions/merged/00029_merged.png357 KB2f260c6b1c36fd18cb567863edcb047746d5c06f8b1aeddd36fae86a0ba6a0f6
eval/ae-decoder-tuning-reconstructions/merged/00037_merged.png399 KB1cf0ca76c738ea24e9db6ea8f17ecb8d487537f5eb12017647629f6afe3c75d6
eval/ae-decoder-tuning-reconstructions/merged/00043_merged.png234 KB9666b39bf0861af76689c2a1d7c50c42b68604fcb57961ca1ef2124c3a84ca7c
eval/ae-decoder-tuning-reconstructions/merged/00051_merged.png447 KBab7a636b203fc844a54b83bce9e5a1a1f6a16d57e4d7dc6e49dde685503f1c9a
eval/ae-decoder-tuning-reconstructions/merged/00053_merged.png535 KB5bd97a0fda66253c103d7fac6746dd47f0be9f7b95ca85b9f4fdea3a48024e5e
eval/ae-decoder-tuning-reconstructions/merged/00055_merged.png485 KB54aae362accbe73e2381ca04a458dbe19dedee3ccb300ab030aebc424345242a
eval/ae-decoder-tuning-reconstructions/original/00011.png133 KB4a811d0ff3ad4a4475772ba337383d48f80c454b69bc531bfa8f96995ae2b943
eval/ae-decoder-tuning-reconstructions/original/00025.png114 KB97daebaa46cf49218a1d4ed7b6f68eea72ea70fe71060151de78258d3e28f408
eval/ae-decoder-tuning-reconstructions/original/00029.png106 KB0f597ae09e23e1bb60c5731b8b350d44ba438e956ff40043ec61035cbca0c52f
eval/ae-decoder-tuning-reconstructions/original/00037.png119 KBa3b63f5338939e8ddc57036d451467a4d8ba8283031bae609433cb4258b36b82
eval/ae-decoder-tuning-reconstructions/original/00043.png68.9 KB8ffea01812789962b616ccad54daf0f4aef1c37868ebc59414bde7e3a0ce25bf
eval/ae-decoder-tuning-reconstructions/original/00051.png134 KB6c03deca85028f0aea37f5d43697760e242d2e807b3e1f8b009cc55dd18ebdf4
eval/ae-decoder-tuning-reconstructions/original/00053.png161 KB4e296dbfd99071223f2ef311931509858ec2cb7b2874b7498627265c4852a5bd
eval/ae-decoder-tuning-reconstructions/original/00055.png146 KB3c7832686419007f5e12ce2456284c5d707080e6216610efc85f6be36644edb2
vae-ft-ema-560000-ema-pruned.ckpt335 MB0b204ad0cae549e0a7e298d803d57e36363760dec71c63109c1da3e1147ec520
vae-ft-ema-560000-ema-pruned.safetensors335 MB95f26a5ab04779d5467d1fcecaf93160ffa523afe399b835b3e1bb77ff2d937a
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
e21db4dc8d pinned now2026-11-15 02:25 UTC36 files · 676 MB

Use it

$ fw get stabilityai/sd-vae-ft-ema-original
# manifest sha256 6cab4215bbaa… · 676 MB · 36 files
$ fw verify ./sd-vae-ft-ema-original stabilityai/sd-vae-ft-ema-original
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/stabilityai/sd-vae-ft-ema-original.json --dir ./sd-vae-ft-ema-original $ python3 fw.py verify ./sd-vae-ft-ema-original ./stabilityai__sd-vae-ft-ema-original.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download stabilityai/sd-vae-ft-ema-original --revision e21db4dc8d4f2675c2ffef479c4c893e83bceada --local-dir ./sd-vae-ft-ema-original
Packaged for ComfyUI. Most image, video and music models run in ComfyUI . Check the publisher's page for the workflow. Freeweights does not host it.
Run at home

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-14
Text in
README.md
Text sha256
1a0f4be40a269cd8c3122599a1215da498f1dab5c6c7e90df3437c12b7dfe330
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: stabilityai <huggingface.co/stabilityai>Newsgroups: alt.freeweights.imageSubject: sd-vae-ft-ema-originalDate: 2026-11-14Commit: e21db4dSigned: 2DC28CC7B26A283B ✓
Upstream
stabilityai/sd-vae-ft-ema-original
Pinned commit
e21db4dc8d4f2675c2ffef479c4c893e83bceada
Manifest
sd-vae-ft-ema-original.json · .minisig
Manifest sha256
6cab4215bbaa30f6fb64f3501fe8587977f2b2919dbc34571b6de2edfcceaa55
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 02:25 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/stabilityai/sd-vae-ft-ema-original.json $ curl -O https://freeweights.allternit.com/manifests/stabilityai/sd-vae-ft-ema-original.json.minisig $ minisign -Vm sd-vae-ft-ema-original.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download stabilityai/sd-vae-ft-ema-original
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. sd-vae-ft-ema-original.json. Provenance. Takedown history: none.
Source
huggingface.co/stabilityai/sd-vae-ft-ema-original

Related models

All of alt.freeweights.image →
From: Comfy-Org <huggingface.co/Comfy-Org>Subject: Boogu-Image
From: Comfy-Org <huggingface.co/Comfy-Org>Subject: Chroma1-HD
From: lodestones <huggingface.co/lodestones>Subject: Chroma1-HD
From: Comfy-Org <huggingface.co/Comfy-Org>Subject: Chroma1-Radiance
From: Comfy-Org <huggingface.co/Comfy-Org>Subject: ERNIE-Image
From: baidu <huggingface.co/baidu>Subject: ERNIE-Image