Simple-Doodle-SD3.5-Turbo

Prompt

Simple Doodle, A cartoon drawing of a woman with long dark brown hair and a white face. The womans face has black eyes, a black nose, and a black smile. She is wearing a peach colored top with a white collar. The background is a light beige color.

Prompt

Simple Doodle, A cartoon drawing of a mountain range with snow on it. The mountain range is outlined in a light green color. There is a pink mountain range in the middle of the mountain range. There are trees in the bottom left corner of the image. The sky is a light blue color and there are clouds in the top right corner. The sun is shining through the clouds.

Prompt

Simple Doodle, A cartoon drawing of a boy with short black hair and a yellow shirt. The boy has a smile on his face. The background is a peach color and there are green leaves on either side of the boy. There are white dots on the peach color background.

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/Simple-Doodle-SD3.5-Turbo

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 & 2300
Epoch	10	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 18

App File Structure

/project-root/

├── .gitattributes
├── README.md
├── app.py
├── pythonproject.py

Setting Up

from diffusers import DiffusionPipeline
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "stabilityai/stable-diffusion-3.5-large-turbo"

torch_dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32

pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
pipe = pipe.to(device)

pipe.load_lora_weights("prithivMLmods/Simple-Doodle-SD3.5-Turbo", weight_name="SD3.5-Turbo-Realism-2.0-LoRA.safetensors")
trigger_word = "Simple Doodle"  
pipe.fuse_lora(lora_scale=1.0)

Trigger words

You should use Simple Doodle to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.