đ Flux.1-Dev-Ctoon-LoRA
This LoRA model is designed for text - to - image generation, aiming to create high - quality cartoon - style images. It is currently in the training phase, and the final version may offer better performance and fewer artifacts.
đ Quick Start
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-Ctoon-LoRA"
trigger_word = "ctoon"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Trigger words
You should use ctoon to trigger the image generation.
⨠Features
- Text - to - Image Generation: Convert text descriptions into cartoon - style images.
- LoRA Integration: Utilize the LoRA technique to fine - tune the base model for specific styles.
đĻ Installation
The weights for this model are available in Safetensors format. You can Download them in the Files & versions tab.
đģ Usage Examples
Here are some examples of using the model:
- Input: 'ctoon, A cartoon drawing of a white cat with a black sunglasses around its eyes. The cats eyes are squinted and the cats ears are a light pink color. There are two yellow stars on the wall to the right of the cat.'
- Input: 'ctoon, A cartoon drawing of a white penguin sitting on a red chair. The penguin has a yellow beak and yellow feet. The background of the penguin is a bright blue color.'
- Input: 'ctoon, A cartoon drawing of a cat wearing sunglasses. The cat is facing towards the left side of the image. It is holding a wine glass with wine in it. There is a bottle of wine to the right of the cat. There are two stars to the left of the animal. The background is a light beige color.'
đ Documentation
Model description
prithivMLmods/Flux.1-Dev-Ctoon-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 |
20 & 2700 |
| Epoch |
15 |
Save Every N Epochs |
1 |
Labeling: florence2 - en(natural language & English)
Total Images Used for Training : 22
Best Dimensions
- 768 x 1024 (Best)
- 1024 x 1024 (Default)
Important Note
â ī¸ Important Note
The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.
đ License
The model is released under the creativeml-openrail-m license.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
