README.md

metadata

tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
  - gta
  - gta6
  - game
  - sdxl
  - StableDiffusionXLPipeline
  - Inference Endpoints
widget:
  - text: >-
      A picture in the style of a gta 5 poster game, GTA V,  Grand Theft Auto 5
      poster,  16k, UHD, HDR, solo human, a blond man with a beard and glasses,
      in a formal suit
    output:
      url: images/GTA11.png
  - text: >-
      A picture in the style of a gta 5 poster game, GTA V,  Grand Theft Auto 5
      poster,  16k, UHD, HDR, Liam Gallagher, moody, wearing a fishtail parka 
    output:
      url: images/GTA12.png
  - text: >-
      John Wick as a GTA San Andreas cartoon, John Wick imagined as a cartoon
      drawing from Grand Theft Auto
    output:
      url: images/GTA13.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: Gta
license: creativeml-openrail-m

Beta-GTA

Prompt

A picture in the style of a gta 5 poster game, GTA V, Grand Theft Auto 5 poster, 16k, UHD, HDR, solo human, a blond man with a beard and glasses, in a formal suit

Prompt

A picture in the style of a gta 5 poster game, GTA V, Grand Theft Auto 5 poster, 16k, UHD, HDR, Liam Gallagher, moody, wearing a fishtail parka

Prompt

John Wick as a GTA San Andreas cartoon, John Wick imagined as a cartoon drawing from Grand Theft Auto

Model description

Pegasi-Beta-GTA-LoRA Image Processing Parameters

Parameter	Value	Parameter	Value
LR Scheduler	constant	Noise Offset	0.03
Optimizer	AdamW	Multires Noise Discount	0.1
Network Dim	64	Multires Noise Iterations	10
Network Alpha	32	Repeat	20
Epoch	15	Save Every N Epochs	1

SETTING-UP

    pipe = StableDiffusionXLPipeline.from_pretrained(
        "SG161222/RealVisXL_V4.0",
        torch_dtype=torch.float16,
        use_safetensors=True,
    )
                    (or)
-----------------------------------------------------------
    pipe = StableDiffusionXLPipeline.from_pretrained(
        "stabilityai/stable-diffusion-xl-base-1.0",
        torch_dtype=torch.float16,
        use_safetensors=True,
    )
    pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
    
    pipe.load_lora_weights("prithivMLmods/Pegasi-Beta-GTA-LoRA", weight_name="Pegasi-Beta-GTA-LoRA.safetensors", adapter_name="gta")
    pipe.set_adapters("gta")
    pipe.to("cuda")

Trigger prompts

A picture in the style of a gta 5 poster game, GTA V,  Grand Theft Auto 5 poster,  16k, UHD, HDR, solo human, a blond man with a beard and glasses, in a formal suit


A picture in the style of a gta 5 poster game, GTA V,  Grand Theft Auto 5 poster,  16k, UHD, HDR, Liam Gallagher, moody, wearing a fishtail parka 


John Wick as a GTA San Andreas cartoon, John Wick imagined as a cartoon drawing from Grand Theft Auto 

Parameter	Value
Prompt	John Wick as a GTA San Andreas cartoon, John Wick imagined as a cartoon drawing from Grand Theft Auto
Sampler	euler

Trigger words

You should use Gta to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.