CivArchive
    ReV Animated - v1.1
    NSFW
    Preview 205669
    Preview 205668
    Preview 205667
    Preview 205665
    Preview 205664
    Preview 205663
    Preview 205662
    Preview 205660
    Preview 205658
    Preview 205657
    Preview 205656
    Preview 205655
    Preview 205654

    April 28, 2024: added V2 Rebirth pruned

    v2:REBIRTH

    Thanks to S6yx for the creation of this beautiful model. Enjoyed by millions. With their permission, I, Zovya, will be maintaining it moving forward.

    April 4, 2024: fp16 and +VAE added

    April 2, 2024: Rebirth

    Update 3: Disclaimer/Permissions updated

    Update 2: I am no longer maintaining/updating this model

    Update 1: I've been a bit burnt out on SD model development (SD in general tbh) and that is the reason there have not been an update. Looking to come back around and develop again by next month or so.Thank you everyone who sends reviews and enjoy my model

    Pay attention to the About this version section of model page for specific version information. ➡️➡️➡️➡️➡️


    Model Overview:

    • rev or revision: The concept of how the model generates images is likely to change as I see fit.

    • Animated: The model has the ability to create 2.5D like image generations. This model is a checkpoint merge, meaning it is a product of other models to create a product that derives from the originals.

    • Kind of generations:

      • Fantasy

      • Anime

      • semi-realistic

      • decent Landscape

    • LoRA friendly

    • It works best on these resolution dimensions:

      • 512x512

      • 512x768

      • 768x512

    VAE:

    Prompting:

    • Order matters - words near the front of your prompt are weighted more heavily than the things in the back of your prompt.

    • Prompt order - content type > description > style > composition

    • This model likes: ((best quality)), ((masterpiece)), (detailed) in beginning of prompt if you want anime-2.5D type

    • This model does great on PORTRAITS

    Negative Prompt Embeddings:

    Video Features

    Olivio Sarikas - Why Is EVERYONE Using This Model?! - Rev Animated for Stable Diffusion / A1111

    Olivio Sarikas - ULTRA SHARP Upscale! - Don't miss this Method!!! / A1111 - NEW Model

    AMAZING SD Models - And how to get the MOST out of them!

    Disclaimer (Updated 10/31/2023):

    The license type is CC BY-NC-ND 4.0
    Do not sell this model on any website without permissions from creator (me)

    Credit me if you use my model in your own merges

    You can use derivative models which uses ReV Animated for Buzz points and site-based currency that does not convert over to real world currency.

    Do not use this model to monetize on other platforms without expressed written consent.

    Description

    • Same Base U-Net Block Merge as initial version

    • Same models used however used weighted sim merge script by RecoilMe (Link to script)

    • Added 10% of TheAlly's Noise Offset for True Darkness in SD (R1.1+(Noiseoffset - SD1.5) @ 0.1 difference)

    • Better results with CLIP 2

    • Smaller model file size

      Prompt recommends:
      ((best quality)), ((masterpiece)), ((realistic)), (detailed)

    FAQ

    Comments (26)

    ktiseos_nyxMar 6, 2023· 1 reaction
    CivitAI

    Yoinked, going to send it to my drive later <3

    s6yxMar 6, 2023· 1 reaction

    teehee

    ritcher1Mar 6, 2023· 3 reactions
    CivitAI

    A really great model !

    Can you add, if possible, a smaller 2gb pruned fp16 no-vae safetensor version ?

    s6yxMar 6, 2023

    theres no way to reduce it to 2gb, max i can drop it to is 4gb with fp16 version

    ritcher1Mar 7, 2023

    Ok, thanks.

    davizcaMar 6, 2023
    CivitAI

    Coul you put the exact formula to add noise offset at 0.1 to any model? Difference mode. Model A (custom model), model B (true SD) and 1.5 model C? at 0.1 Model A?

    s6yxMar 6, 2023

    up to you, i used 0.1 because i didnt want my models being too dark or being more of a realistic model, but at the same time have some good looking deep black gradients. That forumla is exactly how i described in the version desc

    K1ngPRIMESMar 8, 2023
    CivitAI

    I have a question, I love CHECKPOINT, but when I use any anime LORA the intelligence creates images like a guanche or water painting. It is extremely difficult to remove, even with several commands, and it still doesn't come out 100%.

    "I would like to create semi-realistic with the anime lora, but it comes out as painting".

    Does anyone know how to solve this? Thank you in advance.

    BadensteinMar 9, 2023· 1 reaction

    I haven't used the latest version yet but I found that If you use the hi-res fix, on latent, set at 1.5 scale and 0.45 denoising strength, it gets rid of that effect. You may also need to lower your LORA weight prompt a little.

    K1ngPRIMESMar 10, 2023· 1 reaction

    @Badenstein Thank you very much for the tip, I will test it, if it works I will let you know.

    :)

    itsDimmyMar 8, 2023
    CivitAI

    ReVAnimated_v11 checkpoint, but where I change Model to 1REVA_REV_1.1c. ? HELP. Begginer here. ;D (or I'm tripping)

    s6yxMar 8, 2023· 1 reaction

    its the same model, I just name my test checkpoints so i can keep track.

    vortex71Mar 9, 2023
    CivitAI

    ciao! one question.. where i can download the Remacri Upscaler?

    thank you!

    s6yxMar 9, 2023· 1 reaction

    mentioned in description of v1.0 - https://umiai.allsync.com/s/zwXgGNF2H459fQk

    vortex71Mar 9, 2023

    @s6yx ah sorry I had not seen .. thanks

    SD_AI_2025Mar 9, 2023· 2 reactions

    Always prefer trusted sources...

    You find upscalers here

    https://upscale.wiki/wiki/Model_Database

    And from there remacri download links :

    https://u.pcloud.link/publink/show?code=kZgSLsXZ0M1fT3kFGfRXg2tNtoUgbSI4kcSy

    https://drive.google.com/file/d/1lELx_WiA25_S8rYINm_DyMNpFOhfZAzt/view

    vortex71Mar 9, 2023· 1 reaction

    @hansolocambo thx for your support!

    s6yxMar 9, 2023

    @hansolocambo ?? the source is fine that I provided. Bit underhanded to say I would link something untrustworthy

    SD_AI_2025Mar 10, 2023· 2 reactions

    @s6yx I wasn't talking about your link in particular, which I'm sure is fine. Sorry for completely understandable misunderstanding. It was more meant in general : taking from a trusted source is always preferable to a mirrored source.

    SD_AI_2025Mar 9, 2023· 3 reactions
    CivitAI

    READ MODEL VERSION DESCRIPTION ABOUT VAE THAT DIRECTLY AFFECTS STYLE RESULTS

    Could you please state the VAE name, I can't seem to find that info in the page.

    Thanks.

    offshoretrashMar 9, 2023· 4 reactions

    It is under the v1.0 description:

    Vae:

    orangemix.vae.pt - will give you more anime-like result, less 3D-like. More NSFW outputs, sfw if specified.

    kl-f8-anime2.ckpt - will give you a more 3D type anime model, anime/cartoon aspect but more realistic. less NSFW unless specified.

    SD_AI_2025Mar 9, 2023· 2 reactions

    @offshoretrash Oh wow. I didn't even notice that we could actually... click ! on the version number, and get more info. Damn...

    Thanks :)

    maxXmeridiusMar 22, 2023

    I always get an error on the orangemix vae, it tells me that it produces NANs when I do HighRes Fix like 1/5 of the times. If I use argument disable nans check it doesn't give the error but some images become black. Only with highres fix. Can someone tell me if you have the same problem?

    PS: this happens with all NAI vae, so also the Anythingv3 one

    NucccMar 24, 2023

    @offshoretrash They are't good enough for this perfect model....

    RomazeoMar 9, 2023
    CivitAI

    Do you plan to add inpainting for 1.1?

    s6yxMar 9, 2023· 2 reactions

    whenever i have a chance

    Checkpoint
    SD 1.5
    by Zovya
    Download (Beta) View on CivitAI
    anime
    portraits
    illustration
    base model
    cartoon
    fantasy

    Details

    Downloads
    41,473
    Platform
    CivitAI
    Platform Status
    Available
    Created
    3/6/2023
    Updated
    5/14/2026
    Deleted
    -

    Files

    revAnimated_v11.ckpt

    Size:
    5.28 GB
    SHA256:
    acfd73b8a79160750eec2bc4ebac65e83b0eec25174d2bc8032a3fdb1bcfcd80

    Mirrors

    HuggingFace (4 mirrors)
    CivitAI (1 mirrors)

    revAnimated_v11.safetensors

    Size:
    5.28 GB
    SHA256:
    d725be5d187c172fbabfb2d35cf6bff2237367a8c1cf743d03c1c0e57f0e43fa

    Mirrors

    HuggingFace (31 mirrors)
    CivitAI (1 mirrors)