CivArchive
    Spawn - LoHa - v1.20
    NSFW
    Preview 746365
    Preview 746384
    Preview 746358
    Preview 746352
    Preview 746351
    Preview 746361
    Preview 746350
    Preview 746368
    Preview 746349
    Preview 746353
    Preview 746357
    Preview 746371
    Preview 746376
    Preview 746374
    Preview 746378
    Preview 746379
    Preview 746380
    Preview 746370

    Please check out my Ko-Fi page if you are interested in supporting me.

    LoRA commissions open! -> Fiverr

    This is a LoHa LoRA! You need the extension! Why? They do a lot better with multi-concepts.

    Trigger words for V1.20:

    For original clothes: <lora:Spawnv120:0.8>(spawn, red cape, chains, green eyes)

    Follow the steps in the Model Version notes to reproduce my images.

    Sample images generated from Hassaku.

    All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.

    It was trained on 149 512x512 images scraped from the internet and 20 epochs using animefull_final.

    Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned for specific tags.

    Description

    Generate using a weight of 0.4-1 like this: <lora:Spawnv120:0.8>


    How I archived my generations:

    1. txt2img: DPM++ SDE Karras with 20 steps,512x512(can go up to 768 for wide or tall), Restore faces on (using CodeFormer weight 1.0 in Settings), Hires-fix on, to 1024x1024 (double original size) with your preferred upscaler and Denoise 0.5, CFG 7. Then send to img2img!

    2. img2img: DPM++ SED Karras with 20 steps, Restore faces on (CodeFormer weight 1), rescale to 1536x1536, CFG 7, Denoise between 0.3-0.7 (based on how much you want to improve the image), SAME PROMPT! Send to extras when happy with img2img/inpaint results.

    3. extras: Scale to x3 (final will be 4608x4608, I suggest going lower, I did x3 just for the samples here) Upscaler 1 - FatalAnime 4x, Upscaler 2 - SwinIR 4x with 0.10 visibility, GFPGAN 0.10 visibility, CodeFormer 0.10 visibility.

    FAQ

    Comments (6)

    olekingcole001May 11, 2023
    CivitAI

    Just searched for this like yesterday and didn't see anything, but I left the search page up and moved on. Came back today and there's a new model there. Do you read minds?

    Seriously though, this looks great- can't wait to try it!

    Part_LoRAs
    Author
    May 12, 2023

    Nah, just wanted to do something different :)

    I hope you like it.

    Darkcat82Jul 17, 2023
    CivitAI

    I hope you make this available to “Draw Things App” this is the right kind of tone I’d like for my comics

    Part_LoRAs
    Author
    Jul 17, 2023

    I have no idea what is that

    Darkcat82Jul 17, 2023

    @Part_LoRAs It’s an iPhone, iPad Pro, application. It’s called draw things

    GeekyzillaJul 18, 2023
    CivitAI

    Awesome work, dude!

    LoCon
    SD 1.5

    Details

    Downloads
    906
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/10/2023
    Updated
    4/30/2026
    Deleted
    -
    Trigger Words:
    spawn
    red cape
    chains
    green eyes

    Files

    spawn-000020.safetensors

    Mirrors

    TensorFiles (1 mirrors)