metadata
license: other
license_name: bespoke-lora-trained-license
license_link: >-
https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- style
- nostalgia
- game screenshot
- ps1 style
- console graphics
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: ps1
widget:
- text: >-
ps1 game screenshot, the flash in a wheelchair, winning the boston
marathon, hot streaks behind him as his wheelchair drives across the
finish line, there is a banner overhead at the finish line with text ps1
flux by veryvanya, the flashs wheelchair is sleek and high-tech, with
glowing blue accents and a bold, red stripe running along the side, his
iconic red and gold costume is torn and worn, but still vibrant, with a
few loose threads and scorch marks, the finish line is crowded with
cheering spectators, the sky above is a bright, sunny blue, with a few
puffy white clouds, the flashs face is set in a determined expression, his
eyes fixed intently on the finish line, his arms are muscular and toned,
with a few scars and bruises visible, the wheelchairs wheels are blurred,
conveying a sense of speed and motion, the hot streaks behind the flash
are long and curved, like a comets tail, and are colored in shades of
orange, yellow, and red, the banner overhead is made of a shiny, metallic
material, and the text ps1 flux by veryvanya is written in bold,
graffiti-style letters
output:
url: 24439220.jpeg
- text: >-
ps1 game screenshot, a little strawberry hamster floating on a large green
leaf on a gentle river
output:
url: 24440109.jpeg
PS1 Style Flux
Model description
works best when you include 'ps1 game screenshot' in prompt
late 90s/early 2000s ps1/n64 console graphics.
5000 steps
trained on 15 gpt4o captioned and adjusted ps1/n64 game screenshots using https://github.com/ostris/ai-toolkit/tree/main
Trigger words
You should use ps1
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('veryVANYA/ps1-style-flux', weight_name='ps1_style_flux_v1.safetensors')
image = pipeline('`ps1`').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers