ArtificialGuyBR

Home / Blog / Training LoRAs

Doodle.Redmond LoRA: Hand-Drawn Doodle Style for SDXL

Generate clean doodle illustrations with this SDXL LoRA. Trigger words, usage guide, and examples.

2 sources cited Training LoRAs

On this page

  1. What This Model Does
  2. Trigger Words & Usage
  3. Recommended Settings
  4. Examples
  5. License
  6. Common Errors and Fixes
  7. FAQ
  8. Sources
  9. Related Models

Doodle.Redmond – Doodle Hand-Drawing Style LoRA for SDXL

TL;DR

What This Model Does

Doodle.Redmond is a Low-Rank Adaptation (LoRA) trained on top of Stable Diffusion XL 1.0 that specializes in generating hand-drawn doodle style images. The model was created by ArtificialGuyBR with GPU compute sponsored by Redmond.AI.

Unlike photorealistic or painterly LoRAs, this one outputs a consistent marker/pen sketch aesthetic: clean line work, minimal shading, white backgrounds, and a playful cartoon-like quality. It handles diverse subjects — characters, animals, objects, scenes — while keeping the doodle style coherent.

Doodle style example: husky dog sketch

Trigger Words & Usage

Include doodle and/or doodleredm in your prompt to activate the style. The HuggingFace card shows prompts formatted as:

A drawing of [subject], doodle, DoodleRedm

diffusers (Python)

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    'stabilityai/stable-diffusion-xl-base-1.0',
    torch_dtype=torch.float16
).to('cuda')

pipeline.load_lora_weights(
    'artificialguybr/doodle-redmond-doodle-hand-drawing-style-lora-for-sd-xl',
    weight_name='DoodleRedmond-Doodle-DoodleRedm.safetensors'
)

image = pipeline('A drawing of alien, caricature, doodle, DoodleRedm').images[0]

Automatic1111 / ComfyUI

Place DoodleRedmond-Doodle-DoodleRedm.safetensors in your models/Lora folder. Add <lora:DoodleRedmond-Doodle-DoodleRedm:0.8> to your prompt (adjust weight 0.7–1.0).

Parameter | Value

|-----------|-------

Base Model | SDXL 1.0 LoRA Weight | 0.7–1.0 Sampler | DPM++ 2M Karras Steps | 20–30 CFG Scale | 5–7 Resolution | 1024×1024 Doodle style example: alien character

Examples

The model card showcases generations across varied prompts:

All share the same clean doodle line-art quality. The style is versatile — it's not locked to a specific subject.

Doodle style example: Pennywise character

License

HuggingFace: Bespoke LoRA-trained license — commercial use requires rental; derivatives allowed; no re-licensing. See license link.

Civitai: Lists Apache 2.0. The discrepancy means you should verify with the author before commercial use.

Common Errors and Fixes

Error | Cause | Fix | Source

|-------|-------|-----|--------

LoRA not applying | Wrong weight name | Use exact filename: DoodleRedmond-Doodle-DoodleRedm.safetensors | HF card Style not appearing | Missing trigger words | Add doodle, DoodleRedm to prompt | HF card Overcooked look | LoRA weight too high | Reduce to 0.7–0.8 | Community practice

FAQ

Q: Does this work with SD 1.5? A: No, it's trained on SDXL 1.0 base only.

Q: Can I merge this LoRA into a checkpoint? A: Yes, diffusers supports fuse_lora() and A1111 has "Merge LoRA" in the Extensions tab.

Q: What's the difference between doodle and doodleredm triggers? A: Both activate the style; using both together is the author's recommended format.

Sources