milliyin/pixel_art_characters_lora_flux_nf4

FLUX Pixel Art Characters — LoRA

Task: Text-to-Image (Pixel Art Characters)
Base: black-forest-labs/FLUX.1-dev • Adapter: LoRA (attention layers)
Hardware: Trained on NVIDIA A100
Updated: 2025-08-26

This LoRA adapts FLUX to generate retro pixel-art characters with consistent silhouettes and limited palettes great for game assets, avatars, and concept iterations.

Keep prompts short and style-focused (see tips below).
License defaults to CC BY-NC 4.0 (non-commercial).

---

✨ Examples

Prompt	Output
pixel art character, with red hair, wearing gray armor, holding no weapon, facing forward
pixel art character, with red hair, wearing brown armor, holding no weapon, facing forward
pixel art character, with brown hair, wearing blue clothing, holding no weapon, facing forward

---

🚀 Quickstart (Diffusers)

import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    torch_dtype=torch.float16
).to("cuda")

pipe.load_lora_weights("milliyin/pixel_art_characters_lora_flux_nf4")


NEGATIVE_PROMPT = "blurry, low quality, distorted, ugly"
HEIGHT = 512
WIDTH = 512
GUIDANCE_SCALE = 7.5
NUM_INFERENCE_STEPS = 50
SEED = 42

prompt = "pixel art, rpg adventurer, green cloak, clean outline, limited palette, facing forward"

image = pipe(
  prompt=prompt,
  negative_prompt=NEGATIVE_PROMPT,
  height=HEIGHT,
  width=WIDTH,
  guidance_scale=GUIDANCE_SCALE,
  num_inference_steps=NUM_INFERENCE_STEPS,
).images[0]

image.save("sample.png")