Sketch Fav
Collection
Art & Culture in 3:1 β’ 10 items β’ Updated β’ 8
How to use strangerzonehf/Flux-Sketch-Flat-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("strangerzonehf/Flux-Sketch-Flat-LoRA")
prompt = "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"
image = pipe(prompt).images[0]import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("strangerzonehf/Flux-Sketch-Flat-LoRA")
prompt = "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"
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 | 28 & 3990 |
| Epoch | 20 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 42
| 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 = "strangerzonehf/Flux-Sketch-Flat-LoRA"
trigger_word = "Sketch Flat"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
You should use Sketch Flat to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Base model
black-forest-labs/FLUX.1-dev