Flux.1-Dev-Hand-Sticky-LoRA

Prompt

handstick69, a human hand is holding two small stickers, each with the words "you can do this!" written on them in black text. The left sticker is pink, while the right sticker is yellow, with black text written on it. Behind the hand, there is a plant with green leaves and a white tile floor.

Prompt

handstick69, A close-up view of a persons hand holding a sticker that reads "You Rock" in black letters. The sticker is a light blue ice cream with a smiley face on it. The persons nails are painted a vibrant red nail color. The background is a beige polka dot pattern.

Prompt

handstick69, A close-up view of a white sticker that reads "Stay" in black letters on a white background. The sticker has a black outline of a mountain, a cactus, a sun, and a house on the right side of the sticker. There is a tree in the bottom right corner of the image. There are green leaves in the background behind the sticker, and there is a clear blue sky in the top right corner.

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/Flux.1-Dev-Hand-Sticky-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	17 & 1920
Epoch	10	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 20

Best Dimensions

• 768 x 1024 (Best)
• 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-Hand-Sticky-LoRA"
trigger_word = "handstick69"  
pipe.load_lora_weights(lora_repo)

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

Trigger words

You should use handstick69 to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.