CivArchive
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    The VHS LoRA model is designed to capture the nostalgic look and feel of VHS footage, delivering a versatile range of realistic and artistic VHS-inspired outputs. The Realistic versions (v1-v3) have been progressively trained on expanding and refined datasets of genuine VHS footage, making them ideal for generating true-to-life vintage visuals. The Artistic version, on the other hand, is trained on simulated VHS effects and glitch aesthetics, allowing for a more stylized interpretation of the VHS look. Each version has been optimized through different annotation techniques for unique control and detail, ensuring that users can recreate the vintage VHS vibe with accuracy.

    Base Models:

    Flux, SD3.5, SDXL, Pony

    Versions/Variants:

    - Realistic v1: Trained on tags, focuses on capturing the raw qualities of VHS footage.

    - Realistic v2: Trained on captions, delivering refined results with enhanced context.

    - Realistic v3: Trained on both tags and captions, offering the most balanced and nuanced outputs in terms of detail and realism.

    - Artistic v1: Trained on simulated VHS filters and glitch effects, perfect for creating stylized, retro-glitch visuals.

    Recommended Settings:

    - CFG:

    - Flux: 2.0 - 3.5

    - SD3.5: 4.5 - 7

    - SDXL & Pony: 5 - 7

    - Steps:

    - Flux: 20 - 30

    - SD3.5: 20 - 60

    - SDXL & Pony: 30 - 60

    Additional Information:

    This model works well for both txt2img and img2img workflows, allowing users to seamlessly introduce authentic VHS effects. Combining Realistic and Artistic outputs can provide creative variations, from true-to-life retro footage to experimental glitch art.

    Note:

    This model’s results can vary based on prompt details; experimenting with CFG and step ranges will yield different degrees of fidelity to VHS qualities, particularly in Realistic vs. Artistic modes.

    Description

    FAQ

    Comments (7)

    vbobMay 25, 2024· 4 reactions
    CivitAI

    Please make more of these!

    zwaetschge
    Author
    May 25, 2024

    Would love to. Any ideas / suggestions?

    vbobNov 16, 2024· 1 reaction

    do specific movies...that will create a variety!

    zwaetschge
    Author
    Nov 16, 2024

    @vbob already did some, but will do more in the future :)

    yessy_boemJun 3, 2024· 3 reactions
    CivitAI

    so i understand correct that it makes VHS graphics and depicts 90's images? Looking for a 90s style lora for a while now. We could also collaborate on one : )

    zwaetschge
    Author
    Jun 3, 2024· 2 reactions

    correct. maybe you heard of skycorphomevideo. they do it like this, that they actually film the footage with normal cameras,export this to a VHS and rerecord it from the VHS, which gives the natural VHS filter, but with almost no of those fake artifacts added in the filters you find in most apps. but tbf, this version depends fully on one video, where I extracted the frames as a test and its one of my earlier loras lol. so you will have a bit of hard time to get rid of blue background or the plant on the left side of the screen. planning on releasing a new version soon. I'm open for collaboration, you can reach me via dm :)

    yessy_boemJun 6, 2024· 1 reaction

    @zwaetschge sended you a DM!

    LORA
    SDXL 1.0

    Details

    Downloads
    330
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/1/2024
    Updated
    5/20/2026
    Deleted
    -

    Files

    90stutorial.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    479224_training_data.zip

    Mirrors

    CivitAI (1 mirrors)