metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Sketch-Flat
- Beige
widget:
- text: >-
Sketch Flat: A black and white pencil sketch of a Starship rocket launch
is depicted on a beige background. The rocket is captured mid-ascent, with
flames and smoke billowing dramatically from its engines. The body of the
Starship is sleek and cylindrical, detailed with fine lines to emphasize
its metallic surface. Thin, wavy strokes illustrate the clouds of exhaust
expanding at the base. In the background, faint outlines of a launch tower
and distant hills are visible, adding depth to the scene. Above the
rocket, the words "Reaching for the Stars" are written in bold, curved
black ink, , the booster fire smoke was Orange coloured
output:
url: images/10.png
- text: >-
Sketch Flat, A black and white sketch of a mans face is depicted on a
beige background. The mans head is tilted slightly to the left, and his
eyes are slightly open. His hair is a dark shade of black, and he has a
beard and mustache. He is wearing a tie, and a shirt with a collar around
his neck. His ears are sticking out of the top of his head
output:
url: images/1.png
- text: >-
Sketch Flat: A black and white pencil sketch of a train passing through
the base of Mt. Fuji is depicted on a beige background. The train is sleek
and modern, with its carriages connected in smooth lines, racing along a
set of tracks. In the distance, Mt. Fuji looms dramatically, its iconic
peak erupting with streams of bright orange lava, contrasting against the
monochromatic sketch. The lava flows down the mountain in jagged, fiery
streaks, while wisps of smoke and ash rise into the sky, blending into the
horizon with bold, textured strokes. Thin, faint lines of trees and small
houses in the foreground emphasize the scale of the erupting mountain.
output:
url: images/12.png
- text: >-
Sketch Flat, A black and white portrait of a man with a beard and
mustache. The mans face is white and he has dark eyes. His hair is cut up
in a bun. He is wearing a white collared shirt and a white tie. The
background is a light beige color, red eyes
output:
url: images/2.png
- text: >-
Sketch Flat, A black and white sketch of a mans face is drawn on a beige
background, s mouth is slightly open. His hair is slicked back, and he has
a mustache and beard. He is wearing a collared shirt, and a tie. Above his
head is a line of words that are written in black ink, adding a touch of
texture to the image
output:
url: images/3.png
- text: >-
Sketch Flat, a pencil sketch of a mans face is visible on a beige paper.
The mans head is encircled by a series of words, including "You are a good
man." The man has a serious expression on his face, and his eyes are
slightly open. His hair is slicked back, adding a touch of texture to his
face. He is wearing a collared shirt, and a long-sleeved jacket. The shirt
is tucked into his neck, and the jacket is tucked under his collar. The
sketch is done in black ink, with the mans eyebrows and mustache visible.
The background of the paper is a light beige, and there is a yellow dot at
the bottom left corner.
output:
url: images/4.png
- text: >-
Sketch Flat: A fine-lined black and white portrait of Nikola Tesla is
depicted on a beige paper. He is sitting in a thoughtful pose, with one
hand resting against his cheek. His neatly trimmed mustache and sharp
features are accentuated with shading. Behind him, faint outlines of
electrical sparks and waves ripple across the background, emphasizing his
groundbreaking work in energy and magnetism.
output:
url: images/5.png
- text: >-
Sketch Flat: A black and white pencil sketch of Elon Musks face is drawn
on a beige background. His head is slightly tilted, and his eyes have a
thoughtful expression. His neatly combed hair is sketched with fine
strokes, and his faint smile adds a calm demeanor to the image. He is
wearing a collared shirt and a blazer.
output:
url: images/6.png
- text: >-
Sketch Flat: A pencil sketch of a rabbit sitting in a field of grass is
shown on a beige canvas. The rabbit has long, pointed ears and is slightly
turned to the side, as if listening intently. Its fur is softly shaded,
and its tiny nose is accentuated with darker strokes. Surrounding the
rabbit are faint sketches of clover leaves, adding a delicate touch to the
scene.
output:
url: images/7.png
- text: >-
Sketch Flat: A black and white pencil sketch of a fox is drawn on a beige
background. The foxs head is slightly tilted to the right, and its eyes
are wide open with a curious expression. The fur is detailed with fine
lines, emphasizing its bushy tail .
output:
url: images/8.png
- text: >-
Sketch Flat: A black and white pencil drawing of a peacock is featured on
a beige background. The peacocks body is small, but its elaborate feathers
spread wide, detailed with intricate patterns of circles and lines. Its
head is tilted slightly, and a crest of feathers is perched on top. The
tail feathers fade into soft strokes at the edges of the sketch.
output:
url: images/9.png
- text: >-
Sketch Flat, sketch of a yellow hugging face emoji with big hands,
minimalist, impressionism, negative space, flat beige background
output:
url: images/11.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Sketch Flat
license: apache-2.0
Model description for Flux-Sketch-Flat-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 | 28 & 3990 |
Epoch | 20 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 42
Best Dimensions & Inference
Dimensions | Aspect Ratio | Recommendation |
---|---|---|
1280 x 832 | 3:2 | Best |
1024 x 1024 | 1:1 | Default |
Inference Range
- Recommended Inference Steps: 30–35
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 = "strangerzonehf/Flux-Sketch-Flat-LoRA"
trigger_word = "Sketch Flat"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Trigger words
You should use Sketch Flat
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.