💖 Support My Work & Explore More
If this model is useful to you, your support helps me keep publishing free models and open-source AI tools.
Patreon: Support on Patreon
Ko-fi: Buy me a Ko-fi
Buy Me a Coffee: Buy me a Coffee
Discover more of my models, projects, and practical AI resources:
Portfolio: artificialguy.com — models, projects, and experiments.
Prompt library: FindGoodPrompt — curated prompts for image and language models.
AI tools directory: JustGoodAI — a curated directory of useful AI tools.
Twitter/X: @artificialguybr — new models announced here first.
ColoringBook.Redmond is here!
Introducing ColoringBook.Redmond, the ultimate LORA for creating Coloring Book images!
I'm grateful for the GPU time from Redmond.AI that allowed me to make this LORA! If you need GPU, then you need the great services from Redmond.AI.
Test all my Loras here for free and unlimited. Thanks, HF, for Inference API!
It is based on SD XL 1.0 and fine-tuned on a large dataset.
The LORA has a high capacity to generate Coloring Book Images!
The tag for the model:ColoringBookAF
I really hope you like the LORA and use it.
Description
FAQ
Comments (6)
Didn't work with CrystalClearXL
With 1.0 lora strength its not far away from original sdxl, but force lora strength to 1.6 and 2.0 image finally starts to vary much more. I didn't excessive test, just some samples. I used comfyui, so maybe in other GUI, it behaves another way.
I used Automatic to test.
Works great, super results. Kids will be thrilled :) Just keep in mind that it works only with sd_xl_base_1.0_0.9vae model. Initially I've been trying to run it on sd_xl_base_1.0 but nothing worked.
do you have it for SD 1.5 version?
Could you make a Lora to make themed topdown Mazes or 3D mazes like you'd see in some KDP activity books? (like the maze be the roads of a town, or made of logs, etc).
I've been trying to use Controlnet to convert simple maze's 2D (thickened) lineart into something more beautiful (like a hedge maze, a forest maze, an ancient temple) and it's being hard. Most checkpoints seem to have almost no data on how objects look 100% from above so they mess up a lot. If you care to try I noticed Sketch processors seem do it best (often need to switch to 1.8~ weight and "My Prompt Is More Important"). In XL the Sai Sketch processor was giving me the best result (but haven't tested enough in XL).
Alternatively it would be awesome to convert thickened maze lineart into faux 2D videogame levels (like a level in hollow knight, or Braid, DK country, or any 2D Mario games). But again, most checkpoints I've tried can't pull it off. It would be an awesome tool to make puzzle books or even to conceptualize/mockup actual video game levels.