CoolFace
Modelpublic

cahlen/oc-punk-flyer-sdxl-lora

sourceHugging Facecreativeml-openrail-mupdated 7mo agoView on Hugging Face
2likes11downloads
Model Card

OC Punk Flyer LoRA — Orange County California Punk Art Style

A LoRA fine-tune of SDXL 1.0 trained on Orange County, California punk rock flyer art from 1978–2000. Generates high-contrast Xerox-style collages, cut-and-paste zine aesthetics, skull/skeleton motifs, and Southern California beach-nihilism imagery in the visual language of the OC hardcore punk scene — the same DIY aesthetic behind bands like Social Distortion, The Offspring, Bad Religion, Agent Orange, and the entire Huntington Beach / Costa Mesa / Fullerton punk underground.

Trigger word: oc-punk-flyer

Example Generations

OC City Vibes

<div style="display: grid; grid-template-columns: repeat(3, 1fr); gap: 8px;">

Huntington Beach — Surf PunkHuntington Beach — Pier WalkCosta Mesa — Strip Mall Decay
[image][image][image]
Irvine — Tract HousesSanta Ana — Downtown GritOrange — Old Towne
[image][image][image]
Tustin — Hangar RuinsLong Beach — Harbor IndustrialIrvine — Suburban Sprawl
[image][image][image]

</div>

Collages

Skulls & HandsSurf & DeathEyes
[image][image][image]
Raised FistTV StaticSuburban Decay
[image][image][image]
AnarchyBeach PunkSkate & Destroy
[image][image][image]

Punk Portraits & Objects

Guitar CloseupMohawk PortraitMosh Pit
[image][image][image]
Combat BootsBurning SuburbsSkeleton Beach
[image][image][image]
Skater PunkBeach NihilismSkulls Collage
[image][image][image]

Usage

With Diffusers

python
import torch
from diffusers import StableDiffusionXLPipeline

pipe = StableDiffusionXLPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    torch_dtype=torch.float16,
    variant="fp16",
)
pipe.load_lora_weights("cahlen/oc-punk-flyer-sdxl-lora")
pipe.set_adapters(["default_0"], adapter_weights=[0.4])
pipe.to("cuda")

image = pipe(
    prompt="oc-punk-flyer, collage of skulls and reaching hands, torn paper edges, xerox photocopy, high contrast, no text, no words, no letters",
    negative_prompt="text, words, letters, writing, typography, font, caption, label, title, headline, sign, logo, watermark, signature, blurry, photorealistic, photo, smooth gradients, 3d render, clean, modern, digital",
    width=768,
    height=1024,
    num_inference_steps=30,
    guidance_scale=7.5,
).images[0]

image.save("punk_art.png")

With ComfyUI / A1111

Load pytorch_lora_weights.safetensors as a standard SDXL LoRA. Use trigger word oc-punk-flyer in your prompt.

Recommended Settings

ParameterRecommendedNotes
LoRA scale0.3–0.5Sweet spot for style without text artifacts. See guide below.
Resolution768x1024Portrait orientation works best (trained at 1024px)
CFG / Guidance7.5Standard SDXL guidance
Steps25–30Diminishing returns past 30
SamplerEuler a, DPM++ 2M KarrasStandard SDXL samplers

LoRA Scale Guide

The most important parameter. Controls how much of the punk flyer style is applied:

ScaleEffectBest For
0.3Light style influence, very cleanCrowd scenes, portraits — subjects that tend to trigger text
0.35Moderate style, mostly cleanGeneral purpose, collages, city scenes
0.4Strong style, good balanceCollages, objects, landscapes — the default sweet spot
0.5Full style, occasional text artifactsSkulls, skeletons, abstract subjects that don't trigger text
0.6+Very strong, likely text artifactsOnly for subjects that never trigger text (abstract, objects)

Text Suppression

This LoRA was trained on punk rock flyers which are inherently text-heavy. The model has learned to associate the style with text/typography elements. To generate clean art without garbled text:

  1. 1.Use LoRA scale 0.3–0.4 (most important)
  2. 2.Add to your prompt: no text, no words, no letters
  3. 3.Add to negative prompt: text, words, letters, writing, typography, font, caption, label, title, headline, sign, logo, watermark, signature
  4. 4.Avoid "performance" prompts — band-on-stage, concert venue, performer compositions strongly trigger text. Use object/scene/collage prompts instead.

Prompt Tips

  • Always start with the trigger word: oc-punk-flyer
  • Collage prompts work best: collage of [subjects], torn paper, xerox texture, high contrast
  • Object-focused prompts stay clean: guitars, boots, skateboards, buildings
  • Scene/landscape prompts work well: burning houses, beach scenes, urban decay, suburban sprawl
  • Add xerox/zine keywords to reinforce the style: xerox texture, xerox photocopy, punk zine, torn paper, cut-and-paste
  • Avoid: poster, flyer, banner, concert, show, performing (trigger text generation)

Training Details

ParameterValue
Base modelstabilityai/stable-diffusion-xl-base-1.0
FrameworkSimpleTuner
LoRA rank / alpha32 / 32
OptimizerProdigy (auto-adjusting LR, initial 1.0)
Batch size x Accum1 x 4 (effective batch 4)
Max steps3,500
Precisionbf16
SNR gamma5
Noise offset0.05
Caption dropout0.20

Dataset

MetricValue
SourcesCornell Digital Library, Internet Archive
Raw scraped2,351 punk flyer images
CuratedTop 200 by programmatic scoring (entropy, contrast, B&W fraction, edge density, aspect ratio, resolution)
After preprocessing402 images (200 original + 200 B&W augmentation + 2 multi-crop)
Repeats2
Effective samples/epoch804
Total epochs~17.4
Caption strategyInstance prompt only (oc-punk-flyer) — style LoRAs learn better when captions describe content only

Why SDXL over FLUX

SDXL 1.0 (3.5B parameters) was chosen over FLUX (12B+) because FLUX's strong photorealistic prior overwhelms rank-32 style LoRAs. SDXL's smaller parameter count is more amenable to specialized art styles at practical LoRA ranks.

Style Reference

This LoRA captures the visual language of Orange County punk/hardcore flyers from 1978–2000:

  • High-contrast Xerox aesthetic — photocopied, degraded, raw
  • Cut-and-paste collage — torn paper, magazine cutouts, layered imagery
  • Skull/skeleton motifs — the universal punk visual shorthand
  • Beach nihilism — palm trees, surf culture subverted with death imagery
  • Suburban decay — tract houses, strip malls, power lines, OC sprawl
  • DIY zine culture — hand-drawn, rough, anti-commercial

License

This LoRA inherits the CreativeML OpenRAIL-M license from the SDXL base model.

Acknowledgments

Training data sourced from public digital archives (Cornell Digital Library, Internet Archive). This LoRA is a tribute to the OC punk and hardcore community and their extraordinary DIY visual culture.