CivArchive
    Eldritch Candid Photography - Retro Themes and Color
    NSFW
    Preview 14393364
    Preview 14393354
    Preview 14393401
    Preview 14393353
    Preview 14393350
    Preview 14393377
    Preview 14393352
    Preview 14393366
    Preview 14393375
    Preview 14393356
    Preview 14393357
    Preview 14393365
    Preview 14393382
    Preview 14393388
    Preview 14393385
    Preview 14393394
    Preview 14393398
    Preview 14393400
    Preview 14393351
    Preview 14393403

    Candid film photography

    Simulating analog photography with an emphasis on film grain and flattened highlights/shadows. I now have two versions, one that leans to more retro 1960s-1980s coloring and a second with much less bias in subject matter and coloring, but both lend your outputs a very pleasant analog film feel.

    My preference is for use with the base SDXL. Some fine tunes overwhelm the subtle texture and color influence of the LoRA. But if you find one that you can recommend, please share your experience with me! I don't do extensive testing across many fine tuned models.

    Keywords are not usually necessary, but to ensure some stronger influence of the LoRA try any of the following:

    • found footage

    • analog film noise

    • grainy photograph

    • light distortions

    • lens flare

    • grunge frame (does not really work with the unbiased LoRA and only sometimes with the retro LoRA)

    Description

    1.0 version

    FAQ

    Comments (7)

    anduxJun 3, 2024· 1 reaction
    CivitAI

    one question, must be summoned with found footage or just selected in automatic1111?

    eldritchadam
    Author
    Jun 3, 2024· 1 reaction

    you don't need any particular keywords - but how you prompt it will influence the output. I tend to prefer the more distressed, washed-out kinds of imagery. I would start with no special prompt words, and if you want more effect add "grainy candid photo" and then emulate mine more if you want a stronger distressed effect

    eldritchadam
    Author
    Jun 3, 2024· 1 reaction

    but even with no special prompting, the LoRA generally steers images toward a much more analog feel than default SD outputs. It also plays well with other LoRAs and at light usage. As just a subtle influence it can make other output feel just a bit more natural and tactile.

    anduxJun 3, 2024· 1 reaction

    thanks i'll post tomorrow

    anduxJun 4, 2024· 1 reaction

    seems checkpoint dependent, nightvision worked, juggernaut looks normal

    eldritchadam
    Author
    Jun 4, 2024· 1 reaction

    @andux quite - things like grain/noise, heavy color cast, flat shadows or highlights, are all technically photographic errors. A checkpoint heavily trained on an ideal photographic output is going to simply ignore the influence of the LoRA. We tell it "I want a kinda bad photo" and the model simply responds "no".

    The strongest results will be with just the base SDXL. Nearly every fine tune will work against the LoRA to some degree or other.

    anduxJun 4, 2024

    @eldritchadam oh now it makes sense thanks

    LORA
    SDXL 1.0

    Details

    Downloads
    975
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/2/2024
    Updated
    5/12/2026
    Deleted
    -
    Trigger Words:
    candid photography

    Files

    EldritchCandids1.0.2.safetensors

    Mirrors

    Available On (1 platform)

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