FLUX.2-Klein-Dotted-Illustration

FLUX.2-Klein-Dotted-Illustration

FLUX.2-Klein-Dotted-Illustration is an adapter LoRA developed for black-forest-labs/FLUX.2-klein-base-9B, designed to transform images into refined hand-drawn dotted illustrations. The model applies dense pointillism with carefully varied dot sizes and spacing to define form, depth, and shading while strictly preserving the subject’s identity, pose, proportions, and overall composition. It produces clean, print-ready results with natural ink density transitions, subtle organic imperfections, and a timeless editorial illustration aesthetic.

Quick Start with Diffusers

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image

# Switch to "mps" for Apple devices
pipe = DiffusionPipeline.from_pretrained(
    "black-forest-labs/FLUX.2-klein-base-9B",
    torch_dtype=torch.bfloat16
).to("cuda")

pipe.load_lora_weights("prithivMLmods/FLUX.2-Klein-Dotted-Illustration")

prompt = "dotted illustration"

input_image = load_image(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
)

image = pipe(image=input_image, prompt=prompt).images[0]

Trained on ModelScope.cn

Trigger Prompt

Use the following prompt to activate the dotted illustration behavior:

dotted illustration

Detailed Prompt

Transform the image into a hand drawn dotted illustration using dense pointillism with carefully varied dot sizes and spacing to define form depth and shading, minimal or no line work, rendered in monochrome black ink on subtly textured off white paper, strictly preserving the subject’s identity pose proportions and overall composition, maintaining clear facial structure and recognizable features, with natural ink density transitions and slight organic imperfections, finished as a refined editorial print style poster that feels handcrafted and timeless, avoiding photorealism digital gloss color gradients or modern effects.

Download Model

You can download the model files from the Files & versions tab:

Download