Create & Edit Images Instantly with Grok Imagine

Try Grok Imagine
Skip to main content
 - V0.7.4.3-release-bakedVAE thumbnail

- V0.7.4.3-Release-BakedVAE

by ModelsLab
v0743releasebakedvae
Text to Image Community ModelFree for Premium UsersLLMs.txt

NightVision XL 0.7.4.3 Release Notes

With this version of NightVision XL, you should notice more natural and normal looking bodies, a bit more facial variety, and much more balanced color output vs 0.7.0.2. Bodies also look better naked, with less noticeable shoulder bone caps on very thin subjects, more natural ribs on less thin subjects, and even more natural features on skin like moles, blemishes and stretch marks, and old people actually look old. Something I've noticed anecdotally but haven't tested in detail is that blood on skin (like a bloody lip or a cut for example) looks much more natural and realistic, and water looks more wet and less like painted on glue, however YMMV.

Bodies should now look much better proportioned and much less waifish and stretched out, especially in tall AR images. To be clear, while it's not 100% fixed, I've put a lot of work into trying to fix the stretchy giraffe necks, weirdly long legs and freaky torsos that all of the community models have inherited from base. While I haven't banished it completely, it seems body balance is MUCH better. Further, while the default output of this model continues to be photorealism biased, the model is much less rigid now, and you should be able to achieve other styles such as line art or anime (and more) with just a bit of style prompting.

TLDR Improvements

  • body shapes are much more natural, even in non-square ARs

  • more natural looking skin

  • less rigid, can produce other styles than photoreal much easier now

  • less close up portrait bias

  • Output is less contrasty than 0.7.0.2 and colors are more balanced than 0.6.8.1

09/11/23 Changelog

Backmerges into 0.6.8.1 and 0.6.5.0, and differential merges with (internal only version) 0.7.3.3 which was a WIP model. Added 2 new community loras and an internal fixer lora.

New Community LORAs added

  • polyhedron_all_sdxl

  • NaturalBody

New Internal LORA Added

  • nf_v3-test

Internal LORA Rebalance

  • Nightshift

API PlaygroundAPI Documentation

Input

Select models...

Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.

Output

Idle

Unknown content type

Related Models

Discover similar models you might be interested in

Aston Martin One 77 - 2009 - v1.0 SDXL

Aston Martin One 77 - 2009 - v1.0 SDXL

Columbina - v1.0-SDXL

Columbina - v1.0-SDXL

Sento Isuzu All-in-one - v1.0-SDXL

Sento Isuzu All-in-one - v1.0-SDXL

Converse Lugged Heel Platform - V1

Converse Lugged Heel Platform - V1

ThisIsRealXL - v1.0

ThisIsRealXL - v1.0

Ford Mustang GTD - 2025 - v1.0 SDXL

Ford Mustang GTD - 2025 - v1.0 SDXL

ZxZara - v1.0

ZxZara - v1.0

CLO_pencil_skirt_vintage_V1 - V1

CLO_pencil_skirt_vintage_V1 - V1

J3nniLpz - v1.0

J3nniLpz - v1.0

albedobasexlv31

Nahida V1.0 (LoRA on AnimagineXL4.0) - v1.0

Nahida V1.0 (LoRA on AnimagineXL4.0) - v1.0

NN2 - NNKCSV1

NN2 - NNKCSV1