metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- flux
- flux-dev
- gta
- theme
- visualdesign
widget:
- text: >-
GTA 6 Theme, World of GTA 6, (Masterpiece, best quality:1.2),
(Masterpiece, best quality:1.2), landscape, perspective aerial view,
tropical mountains, landscape indigo accent, mythology, cinematic,
detailed, atmospheric, backlit, epic, cinematic, understanding art, matte
painting, beautiful scenery, Realistic lighting, Masterpiece, Good
quality, Nice graphics, High level of detail, ultra detailed, cinematic
lighting, HDR, Illustration, --v6
output:
url: images/gta1.webp
- text: ' GTA 6 Theme, World of GTA 6, Crumbling City, unreal engine, greg rutkowski, loish, rhads, beeple, makoto shinkai and lois van baarle, ilya kuvshinov, rossdraws, tom bagshaw, alphonse mucha, global illumination, detailed and intricate environment'
output:
url: images/gta2.webp
- text: >-
GTA 6 Theme, World of GTA 6, Post-apocalyptic jungle with bio-mechanical
flora and fauna, cinematic, 4k, epic Steven Spielberg movie still, sharp
focus, emitting diodes, smoke, artillery, sparks, racks, system unit,
motherboard, by pascal blanche rutkowski repin artstation hyperrealism
painting concept art of detailed character design matte painting, 4 k
resolution blade runner
output:
url: images/gta3.webp
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: GTA 6 Theme, World of GTA 6
license: creativeml-openrail-m
Castor-Gta6-Theme-Flux-LoRA
Demo here: https://huggingface.co/spaces/prithivMLmods/FLUX-LoRA-DLC
The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.
Model description
prithivMLmods/Castor-Gta6-Theme-Flux-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 & Steps | 15 & 1K |
Epoch | 10 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 15+ [ Hi-RES ]
Setting Up
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "prithivMLmods/Castor-Gta6-Theme-Flux-LoRA"
trigger_word = "World of GTA 6, GTA 6 Theme" # Leave trigger_word blank if not used.
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Sample
Prompt |
---|
World of GTA 6, Captured at eye-level on a high-angle shot of a highway at sunset. The sky is a vibrant pink, with a few wispy clouds scattered across the sky. The sun is setting, casting a warm glow over the scene. In the foreground, a bridge stretches over a body of water, dotted with trees and a few cars. The bridge is adorned with a white truck with a red sign on the side, adding a pop of color to the scene to the image, GTA 6 Theme |
App File Structure
/project-root/
βββ .gitattributes
βββ README.md
βββ app.py
βββ pythonproject.py
Trigger words
You should use GTA 6 Theme
to trigger the image generation.
You should use World of GTA 6
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.