Other Styles
Collection
illustrations • 20 items • Updated
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Polycruz9/sketch-painterly")
prompt = "Qd Sketch, An abstract painting of a woman in a green t-shirt and black pants. The woman is facing the left side of the frame, her left hand is covering her face with her right hand. Her right hand is positioned in front of her face. Her hair is a dark shade of black, and her eyes are a light brown. Her lips are a darker shade of brown. The background is a peach color, and the womans shirt is a vibrant green."
image = pipe(prompt).images[0]
______ ______ __ __ __ ______ ______ __ __ ______ __ ______
/\ == \/\ __ \ /\ \ /\ \_\ \ /\ ___\ /\ == \ /\ \/\ \ /\___ \ /\ \ /\ __ \
\ \ _-/\ \ \/\ \\ \ \____\ \____ \\ \ \____\ \ __< \ \ \_\ \\/_/ /__ \ \ \\ \ \/\ \
\ \_\ \ \_____\\ \_____\\/\_____\\ \_____\\ \_\ \_\\ \_____\ /\_____\ \ \_\\ \_____\
\/_/ \/_____/ \/_____/ \/_____/ \/_____/ \/_/ /_/ \/_____/ \/_____/ \/_/ \/_____/






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 | 26 & 3830 |
| Epoch | 20 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 23
| Dimensions | Aspect Ratio | Recommendation |
|---|---|---|
| 1280 x 832 | 3:2 | Best |
| 1024 x 1024 | 1:1 | Default |
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 = "Polycruz9/sketch-painterly"
trigger_word = "Qd-Sketch"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
You should use Qd-Sketch to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
# Gated model: Login with a HF token with gated access permission hf auth login