Artius 2-1 V1.0 VAE - Checkpoint for SD 2.1 768

Artius 2-1 - V1.0 VAE

Explore your imagination!
Artuis is a versatile and flexible model, it allows you to generate crisp, high-resolution images:
- Realistic portraits
- N_S_F_W
- Stylized Art
- Logos
- Game assets
- Texture
- People, animals, food photos and more
- Product concept
- Any genre: Realistic, Fantasy, Sci-Fi, Cyberpunk, Anime and more

If you liked my model, please leave a review, it helps other users to find this model and see its features!

This is SD 2.1 based model, also I have SD 1.5 based version: https://civarchive.com/models/47691/artiusv1-5

The model works best with the following samplers:
Euler a
DPM2
DPM++ 2M Karras

Optimal settings:
Clip skip 1
Eta noise seed delta: 31337
DPM++ 2M Karras
25 Steps
CFG Scale 5-6
Resolution from 768 (768, 1024, 1280)

The model is prompt sensitive, so it depends on your imagination.
I've generated some demo images, you can study the prompt and make your own based on them.

To make unique faces, mix faces that the model knows: [person1 : person2 : 0.5]

Description

FAQ

Comments (27)

pursuit_of_beautyApr 1, 2023

CivitAI

From your description:

Artuis is versatile and flexible model

You have a spelling error.

_i3oc9i_Apr 1, 2023

CivitAI

You said that Artius V2.1 NSFW is a demo of NSFW capability of this model but the two model have a different hash, so I assume they are two different models, am I wrong ?

sanchezvfxApr 1, 2023· 1 reaction

Yes, I change hash a little, but the models the same

slbonecast1234Apr 1, 2023

CivitAI

Getting an error

NansException: A tensor with all NaNs was produced in Unet

sanchezvfxApr 1, 2023

https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/6923

bobcamberApr 6, 2023

Same issue

Mech4nimaLApr 6, 2023

did you remember to use the yaml file?

kavellionApr 12, 2023

set batch file as..... set COMMANDLINE_ARGS= --no-half --xformers --no-half-vae --disable-nan-check

aroman1979Apr 2, 2023

CivitAI

Здравствуйте. Скажите, пожалуйста, почему я получаю ошибку RuntimeError: output with shape [320, 320] doesn't match the broadcast shape [320, 320, 320, 320] всякий раз, и как мне ее решить?
С другими моделями такой ошибки не выдает.

sanchezvfxApr 2, 2023

Не сталкивался с такой ошибкой, эта модель сделана на основе Stable Diffusion 2.1 768, попробуйте положить рядом с моделью конфиг файл

aroman1979Apr 2, 2023

@sanchezvfx Спасибо за обратную связь. Я скачивал и положил в ту же папку файл конфигурации artiusV21_v21.yaml (это он же?) Увы, с этим файлом не помогает.

aroman1979Apr 2, 2023

@sanchezvfx убрал ЛОРУ - заработало ... Жаль, что с Лорой не работает =(

sanchezvfxApr 2, 2023

@aroman1979 под SD 2.1 тоже есть лоры, но их пока меньше

aroman1979Apr 2, 2023

@sanchezvfx понял. Дождусь. Спасибо большое за ответы.

ProtoPlazmaApr 2, 2023

CivitAI

What models did you merge?

mishamicki17182Apr 4, 2023

CivitAI

Подскажите как этим пользоваться ?

PostitingApr 5, 2023

CivitAI

I'd like to use this, but neither of your models is recognized in checkpoints.

hfiani262Apr 10, 2023

Did you download the config file and put it just beside the model file?

kavellionApr 12, 2023

Try making your command line like this in batch file. set COMMANDLINE_ARGS= --no-half --xformers --no-half-vae --disable-nan-check

digiart_by_aiApr 5, 2023· 4 reactions

CivitAI

Отличная модель, отлично генерирует пальцы, лица. Смотрю тебя на Ютубе, ты очень талантливый и работы твои очень трудоёмкие. Спасибо за такую отличную модель!

sanchezvfxApr 20, 2023

На здоровье!)

nutronicApr 11, 2023

CivitAI

I see that this was listed under landscapes. Its clearly labeled wrong.

sanchezvfxApr 20, 2023

Because Artius is a universal model that can generate landscapes as well

abhineish339Apr 23, 2023· 1 reaction

CivitAI

Thank you for this model looks good. Appreciate your work and keep going.

zirteqJul 2, 2023· 3 reactions

CivitAI

I used Artius V2.1 to generate a music video with an AI generated prompt progression about a scientist.

https://www.youtube.com/watch?v=G_6bdDrLEik

The higher resolution of this model allowed me to generate the animation frames directly at 1280x720 without creating any twins or duplication artifacts, as conventional 1.5 models usually tend to do at such resolutions.

neon_sin459Jan 20, 2024

nice !

svejationAug 22, 2023

CivitAI

Чуваки подскажите какой VAE вы используете???

У меня есть: для SD - 1.5 vae-ft-mse-840000-ema-pruned

У меня есть: для SD XL - sd_xl_base_1.0_0.9vae

Для SD 2.0 2,1 где VAE взять ? ))

VAE он же типо обработчик моделей!

Dudes tell me which VAE do you use???

I have: for SD - 1.5 way-ft-mse-840000-ema-pruned

I have: for SD XL - sd_xl_base_1.0_0.9vae

For SD 2.0 2.1 , where can I get VAE ? ))

VAE is also a type of model handler!

Checkpoint

SD 2.1 768

by neuroshaman

Download (Beta) View on CivitAI

Details

Downloads

5,922

Platform

CivitAI

Platform Status

Available

Created

4/1/2023

Updated

11/11/2026

Deleted

Files

ArtiusV2.1.safetensors

Size:

2.43 GB

SHA256:

4ee4331304c99d877bc252261103b825fca4cd9d31e3a40079c8d8ab6ec1ecc9

Mirrors

HuggingFace (5 mirrors)

artius21_v10VAE.safetensors

artiusV21_v21.safetensors

CivitAI (1 mirrors)

ArtiusV2.1.safetensors

ArtiusV2.1.yaml

Size:

1.77 KB

SHA256:

72b092aadfe146f5d3f395a720c0aa3b2354b2095e3f10dc18f0e9716d286dcb

Mirrors

CivitAI (83 mirrors)

Old_Portraits.yaml

Mangled_Merge_V3.yaml

URPM_2.1_V2.yaml

KitchenSink2nsfw.yaml

SD2.1_MilfShaper_v1.0(FP16).yaml

ultraskin.yaml

graphic-art-1_1.yaml

djzGrimKnightsV21_0.yaml

Cthugha.yaml

PseudoFreedomMerge.yaml

illuminatidiffusion_v1.1.yaml

wd15-beta2-halo-aesthetic.yaml

CharHelperV4.yaml

graphic-art.yaml

macarolus2.yaml

oxigien_v20_Lite.yaml

SDArt_synesthesia768.yaml

ZphyrRemember.yaml

AllureAI_batch4_v03-ep220.yaml

CharHelper_v1_ SDv2_1_768_step_3500.yaml

CharHelper_v2_ SDv2_1_768_step_8500.yaml

SDArt_Encapsulated768.yaml

KitchenSinkVer1.8L.yaml

rMadaSD21_v6.yaml

oxigien_v20_Epic.yaml

dragonportrait-sd21-768-v1.yaml

ArtiusV2.1.yaml

yai-2.2.14.yaml

yai2.2.20.yaml

vector-art.yaml

concept-sheet.yaml

djzInkPunkV21.yaml

comodel2.yaml

clayitization-SD2.1-768px.yaml

food_crit-SD2.1-768px.yaml

CharHelperV3.yaml

perpetual-v1-moon.yaml

pulp-vector.yaml

KitchenSink2safe.yaml

Ushio_Anime_V1.yaml

yai2.2.20.yaml

URPM_2.1_V1.yaml

realismEngine_v10.yaml

pretty_girls_next_door_v2.yaml

pretty-girls-next-door-v5.1.yaml

pretty_girls_next_door_v6.0.yaml

KitchenSinkVer1.8.yaml

ZphyrInsanity.yaml

SDArt_UnmythicalCreatures768.yaml

CharHelper Fine-Tuned.yaml

SDArt_CosmicHorrors768.yaml

pretty_girls_next_door_v9_0.yaml

oxigien_v20_lite.yaml

woolitize-SD2.1-768px.yaml

ZphyrPortraits.yaml

KitchenSink2safeFP16.yaml

yai-2.2.20-F.yaml

dragonportrait-sd21-768-v2.yaml

PXL8V1.yaml

3DMDT1.yaml

sticker-v1.yaml

PRMJ.yaml

UltraCmodel.yaml

djzDivineStatueV21.yaml

wooditize-SD2.1-768px.yaml

naturitize-SD2.1-768px.yaml

wd-beta3-base-fp16.yaml

SDArt_AliceInDiffusionLand768.yaml

oxigien_v20_ultra.yaml

A-to-Zovya_RPG_Artist_Tools_21_V1.yaml

pulp-diffusion.yaml

classicnegative768px-v0.2.yaml

yai-2.2.14.yaml

YAI2.3.22.yaml

imagineV41_v10.yaml

BoW-config.yaml

SDArt_v1.yaml

SDArt_v2_768.yaml

pretty-girls-next-door-v1.yaml

Mangled_Merge_V2.yaml

SDArt_ChaosAndOrder768.yaml

pretty_girls_next_door_v7_0.yaml

pretty_girls_next_door_v8_0.safetensors.yaml

TensorArt (1 mirrors)

3dmdt1GeneralistModelHigh_v1.yaml

Available On (1 platform)

Same model published on other platforms. May have additional downloads or version variants.

SeaArt

Artius 2-1 - V1.0 VAE

Description

FAQ

What is Artius 2-1?

How do I use Artius 2-1?

What files are available and where can I download them?

Comments (27)

Details

Files

ArtiusV2.1.safetensors

Mirrors

ArtiusV2.1.yaml

Mirrors

Available On (1 platform)