metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Pencil
widget:
- text: >-
Simple Pencil, A pencil drawing of a smiling boy is drawn on a white wall.
The pencil is black with a yellow tip. The boys face is drawn with black
lines. He has short brown hair that is pulled up in a ponytail. His eyes
are open and he has a big smile on his face. His mouth is open and his
teeth are visible. He is standing on a black pole that is attached to the
pencil. The background is plain white.
output:
url: images/SP1.png
- text: >-
Simple Pencil, A black and white pencil drawing of a womans face on a
white paper. Her hair is long and cascades down to her shoulders. Her eyes
are closed and her lips are slightly parted. Her eyebrows are squinted.
Her lips are painted a dark shade of black. She is wearing a necklace
around her neck. Her neck is draped over her chest. Her head is tilted
slightly to the left. Her nose and mouth are also painted black.
output:
url: images/SP2.png
- text: >-
Simple Pencil, A black and white pencil drawing of a small bird on a white
surface. The bird is facing towards the left side of the image, with its
head turned towards the right side. Its beak is black, and its eyes are
black. Its wings are black, while its tail is black. There are two black
pencils on the surface to the left of the bird. The background is a solid
white.
output:
url: images/SP3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Simple Pencil
license: creativeml-openrail-m
Super-Pencil-Flux-LoRA
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/Super-Pencil-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 & 2070 |
Epoch | 13 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 12
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/Super-Pencil-Flux-LoRA"
trigger_word = "Simple Pencil"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Trigger words
You should use Simple Pencil
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.