Flux.1-Dev-LoRA-HDR-Realism [ Experimental Version ]

The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.

Prompt

HDR, Captured at eye-level, a close-up shot of a young woman with dark brown hair and blue eyes. Her hair is styled in a braided bun, and shes wearing a black strapless dress with a black lace trim. She is wearing a gold necklace with a silver charm on it. The backdrop is blurred, and there are several lights hanging from the ceiling, adding a touch of color to the scene.

Prompt

HDR, Captured in a low-angle shot, a medium-sized man with dark brown hair and a goatee is seated on a chair. His eyes are a piercing blue, and his eyebrows are a darker shade of brown. His lips are a lighter shade of pink, and he has a serious expression on his face. He is wearing a gray sweater with a textured pattern on the left side of his chest. His sweater is a light gray, with a black stripe running down the center of the sweater. The backdrop is blurred, and a wooden chair is visible behind the man.

Prompt

HDR, a close-up shot of a womans face is adorned with a layer of snow, adding a touch of warmth to the scene. The womans eyes are closed, her lips are pursed in a deep pink shade, while her hair cascades over her shoulders. Her eyebrows are adorned with small, white snowflakes, adding depth to the composition. The background is blurred, creating a soft, blurred effect.

• Hosted Here🧨: https://huggingface.co/spaces/prithivMLmods/FLUX-LoRA-DLC

Model description

prithivMLmods/Flux.1-Dev-LoRA-HDR-Realism

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	19 & 2000
Epoch	17	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 14

Best Dimensions

• 1024 x 1024 (Default)

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/Flux.1-Dev-LoRA-HDR-Realism"
trigger_word = "HDR"  
pipe.load_lora_weights(lora_repo)

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

Trigger words

You should use HDR to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.