Flux-Toonic-2.5D-LoRA

Prompt

toonic 2.5D, Captured from a low-angle perspective on a vibrant yellow backdrop, a cartoon boy is depicted in a cartoon-like fashion. He is wearing a yellow shirt, blue pants, and white shoes. His arms are outstretched, and his mouth is slightly open, as if he is screaming. His eyes are squinted, and he has brown hair, and a black mustache. His hair is cut in a bob, adding a pop of color to the scene.

Prompt

toonic 2.5D, A digital art painting of a woman in a white shirt, blue pants, and a black hat with white marshmallows in her hair. The woman is standing in front of a blue square with the number 300 on it. The background of the painting is a light gray color.

Prompt

toonic 2.5D, a cartoon character is seated on a white scooter. The scooter is positioned in front of a pink background. The character is wearing a white short-sleeved shirt, a pair of white pants, and white tennis shoes. His right foot is crossed over the scooter, while his left foot is resting on the handlebars. The handlebars are black, while the seat is white with a red stripe down the center. The background is a pale pink, adding a pop of color to the scene.

Prompt

toonic 2.5D, A cartoon drawing of a boy in a white car. The car is black and has a white stripe on it. The boy has brown hair and brown spots on his head. He is holding a white bow in his hand. The background is a light pink color. The front of the car has a black bumper with yellow lights. The headlights are on the car.

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-Toonic-2.5D-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	23 & 2900
Epoch	15	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 15

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-Toonic-2.5D-LoRA"
trigger_word = "toonic 2.5D"  
pipe.load_lora_weights(lora_repo)

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