ArtificialGuyBR

Home / Blog / Training LoRAs

PS1 Game Graphics LoRA for SDXL: Generate Retro PlayStation 1 Style Images

Create PlayStation 1 era game graphics with this SDXL LoRA. Uses trigger words 'Playstation 1 Graphics' and 'PS1 Game' for authentic low-poly aesthetic.

2 sources cited Training LoRAs

On this page

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

PS1Redmond: PS1 Game Graphics LoRA for SDXL

TL;DR

What This Model Does

PS1Redmond is a Low-Rank Adaptation (LoRA) fine-tuned on Stable Diffusion XL 1.0 that specializes in reproducing the distinctive visual style of PlayStation 1 games. The model captures the low-polygon geometry, visible texture warping, limited color palettes, and characteristic pixelated aesthetic that defined the PS1 era.

PS1 style game graphics example showing low-poly character in game environment

Trigger Words & Usage

The model activates with two key trigger phrases:

Both should be included in your prompt for best results. Example prompts from the model card:

harry potter game, playstation 1 graphics, PS1 Game
Assassins Creed, playstation 1 graphics, PS1 Game
emma watson, low poly, playstation 1 graphics, PS1 Game
Racing Game car, yellow ferrari, playstation 1 graphics, PS1 Game
first person shooter, fps, playstation 1 graphics, PS1 Game

How to Use

With 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/ps1redmond-ps1-game-graphics-lora-for-sdxl',
    weight_name='PS1Redmond-PS1Game-Playstation1Graphics.safetensors'
)

image = pipeline('harry potter game, playstation 1 graphics, PS1 Game').images[0]

In ComfyUI / A1111

  1. Download PS1Redmond-PS1Game-Playstation1Graphics.safetensors
  2. Place in your models/loras folder
  3. Add <lora:PS1Redmond-PS1Game-Playstation1Graphics:0.8> to your prompt
  4. Include trigger words: playstation 1 graphics, PS1 Game

PS1 racing game example with low-poly car

Parameter | Recommendation

|---|---

Base Model | stabilityai/stable-diffusion-xl-base-1.0 Resolution | 1024x1024 (SDXL native) LoRA Weight | 0.7 - 1.0 Sampler | DPM++ 2M Karras / Euler a Steps | 20-30 CFG Scale | 5-7

Training Details

PS1 first-person shooter example showing characteristic warping

Common Errors and Fixes

Error | Cause | Fix | Source

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

LoRA not applying | Wrong weight name | Use exact filename: PS1Redmond-PS1Game-Playstation1Graphics.safetensors | HF model card Style not showing | Missing trigger words | Always include playstation 1 graphics, PS1 Game in prompt | Model card examples CUDA OOM | VRAM insufficient | Use --lowvram or --medvram flags, or reduce resolution | diffusers docs

FAQ

Q: Does this work with SD 1.5? A: No, this LoRA is trained specifically for SDXL 1.0 base model.

Q: Can I use this commercially? A: Yes, the Civitai page lists Apache 2.0 license which permits commercial use with attribution.

Q: What weight should I use? A: Start at 0.8 and adjust. Higher weights (1.0) increase PS1 fidelity but may reduce prompt adherence.

Q: Are there multiple versions? A: Only one variant is published on Civitai (model ID 254376).

Sources