Intense-Red-Flux-LoRA

Prompt

Intense Red, a black cat is facing the left side of the frame. The cats head is tilted upward, with its eyes closed. Its whiskers are protruding from its mouth, adding a touch of warmth to the scene. The background is a vibrant red, creating a striking contrast with the cats fur.

Prompt

Intense Red, A black bird is perched on a thin branch. The bird has a black body and a black tail. Its head is turned to the left and its beak is pointed to the right. The background is a vibrant red and there is a shadow of a tree on the right side of the frame. The branch that the bird is sitting on is dark brown and has a few small black spots on it.

Prompt

Intense Red, a silhouette of a man in a black wetsuit stands on a beach, holding a black surfboard in his right hand. The mans shadow is cast on the ground, adding a touch of color to the scene. The background is a vibrant red, creating a striking contrast to the man and his surfboard.

• Hosted 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/Intense-Red-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	22 & 2.65K
Epoch	13	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 22 [ Hi-RES ]

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/Intense-Red-Flux-LoRA"
trigger_word = "Intense Red"  
pipe.load_lora_weights(lora_repo)

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

Data source

- https://freeflo.ai/

Trigger words

You should use Intense Red to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.