prithivMLmods/Canopus-Car-Flux-Dev-LoRA

Car-Flux-Dev-LoRA

Prompt

A black ford mustang parked in the parking lot, in the style of futurism influence, uhd image, furaffinity, focus, street photography, thin steel forms, 32k uhd --ar 2:3 --v 5

Prompt

Ferrari car f3 458 tt, in the style of liam wong, fujifilm x-t4, multiple exposure, tsubasa nakai, uhd image, pinturicchio, crimson --ar 16:9 --v 5.2

Prompt

Bugatti Veyron in cobalt blue metallic, high detail, octane render, 8k

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/Canopus-Car-Flux-Dev-LoRA

Image Processing Parameters

Parameter	Value	Parameter	Value
LR Scheduler	constant	Noise Offset	0.03
Optimizer	AdamW8bit	Multires Noise Discount	0.1
Network Dim	64	Multires Noise Iterations	10
Network Alpha	32	Repeat & Steps	22 & 1.5K+
Epoch	15	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 40+ [ Hi-RES ]

& More ...............

Trigger prompts

A black ford mustang parked in the parking lot, in the style of futurism influence, uhd image, furaffinity, focus, street photography, thin steel forms, 32k uhd --ar 2:3 --v 5

Ferrari car f3 458 tt, in the style of liam wong, fujifilm x-t4, multiple exposure, tsubasa nakai, uhd image, pinturicchio, crimson --ar 16:9 --v 5.2

Bugatti Veyron in cobalt blue metallic, high detail, octane render, 8k

Parameter	Value
Prompt	Bugatti Veyron in cobalt blue metallic, high detail, octane render, 8k
Sampler	euler

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/Canopus-Car-Flux-Dev-LoRA"
trigger_word = "car"  # Leave trigger_word blank if not used.
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

Trigger words

You should use Car to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.