Models>

Yut game board, 윷판, 윷놀이 판

Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is available for use and will generate similar character to the ones seen in the images.

Model Description by Creator

A model to create boards for the Korean traditional board game of yut,

This is not a good model, because I couldn't find very good data, most available boards look like this

so I could only find 20 (!) images that don't look very basic. Half of them are pixelated :(

Prompting/Use:

  • yutpan, x shape, SHAPE, MEDIUM, THEME, masterpiece, best quality

  • SHAPE is 'square' or 'round'

  • MEDIUM is 'traditional, paper' or 'traditional, textile' or 'illustration'

  • THEME is 'animal theme' or 'nature theme' or 'chinese character', etc ....

Prompt with Lora at weight 1.0 (for example with SD1.5 base). The global shape of the board should be ok, but the position markers should look like crap.

Transfer to img2img, change, the model to something you prefer, click 'Only masked' because we want the model to concentrate on this position marker only, reduce the padding (for example to 8, so that the inpaint doesn't see the neighbouring position markers), raise the denoising strength to 0.8 (the lora did a shitty job, the model will have to get creative).

For each position marker:

  • go to the inpaint tab, remove the current image by clicking X on the top right of the image (this avoids automatic1111 remembering the previous inpaint mask)

  • go back to img2img, click inpaint

  • in the inpaint tab, mark one of the position tokens as needing inpaint, by drawing on it

  • modify the prompt, for example 'cat head, sticker' without lora, if you want to avoid a bad halo you will also have to indicate the background color with the prompt

  • click generate

  • if you're happy with the result, click on 'transfer to img2img'

  • repeat 29 times :(

Example:

yutpan, paper, square, x shape, traditional, cat theme <lora:yutpan_merge_mean:1>
Steps: 26, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2063682367, Size: 512x512, Model hash: 812cd9f9d9, Model: Anything-V3.0-pruned-fp16, VAE hash: 1b7c62d2a7, VAE: zVae_v10.safetensors, Denoising strength: 0.35, Clip skip: 2, Hires upscale: 1.5, Hires steps: 13, Hires upscaler: R-ESRGAN 4x+ Anime6B, Lora hashes: "yutpan_merge_mean: 461481682168", Version: v1.6.0

Yes, the position markers look like crap.

After inpainting every position marker on the right side:

Maybe it would be easier to just draw a square with a cross, and generate 29 position markers with 'cat, round, stickers', then remove the background and assemble the board...

Images Generated With This Model

yutpan, illustration, square, x shape, frog theme <lora:yutpan_merge_mean:1>
N/A
Hidden For Public Users
yutpan, illustration, square, x shape, frog theme <lora:yutpan_merge_mean:1>
yutpan, paper, square, x shape, traditional, cat theme <lora:yutpan_merge_mean:1>
N/A
Hidden For Public Users
yutpan, paper, square, x shape, traditional, cat theme <lora:yutpan_merge_mean:1>
yutpan, x shape, square, illustration, iron man theme, best quality, masterpiece <lora:yutpan_merge_mean:1.0>
N/A
Hidden For Public Users
yutpan, x shape, square, illustration, iron man theme, best quality, masterpiece <lora:yutpan_merge_mean:1.0>
yutpan, paper, square, x shape, traditional, cat theme <lora:yutpan_merge_mean:1>
N/A
Hidden For Public Users
yutpan, paper, square, x shape, traditional, cat theme <lora:yutpan_merge_mean:1>
yutpan, x shape, square, illustration, frozen theme, best quality, masterpiece <lora:yutpan_merge_mean:1.0>
N/A
Hidden For Public Users
yutpan, x shape, square, illustration, frozen theme, best quality, masterpiece <lora:yutpan_merge_mean:1.0>
red, frosted glass, hooded man, short hair, paper, sculpt, riddingink, metal, feminine, fabric,roughness ,
N/A
Hidden For Public Users
red, frosted glass, hooded man, short hair, paper, sculpt, riddingink, metal, feminine, fabric,roughness ,
((masterpiece,best quality)), absurdres,
<lora:Duskull_Pokemon_Anime:1>, Duskull_Pokemon, no humans, floating, pokemon \(creature\), , traditional_youkai, 
solo, smiling, looking at viewer,
purple theme, graveyard in background,
N/A
Hidden For Public Users
((masterpiece,best quality)), absurdres, <lora:Duskull_Pokemon_Anime:1>, Duskull_Pokemon, no humans, floating, pokemon \(creature\), , traditional_youkai, solo, smiling, looking at viewer, purple theme, graveyard in background,
((masterpiece,best quality)), absurdres,
<lora:Duskull_Pokemon_Anime:1>, Duskull_Pokemon, no humans, pokemon \(creature\), , traditional_youkai, 
solo, smiling, looking at viewer,
purple theme, graveyard in background,
N/A
Hidden For Public Users
((masterpiece,best quality)), absurdres, <lora:Duskull_Pokemon_Anime:1>, Duskull_Pokemon, no humans, pokemon \(creature\), , traditional_youkai, solo, smiling, looking at viewer, purple theme, graveyard in background,
kagamimochi, head on rice cake,  on square wooden base, a pair fern, paper between rice cake to wooden base
<lora:kagamimochi-001_0.7:1>
N/A
Hidden For Public Users
kagamimochi, head on rice cake, on square wooden base, a pair fern, paper between rice cake to wooden base <lora:kagamimochi-001_0.7:1>

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.