DoozyWo/Kontext_avatar_LoRA

FLUX.1-Kontext-Dev Na'vi Style LoRA 🎨🧞‍♂️

This is a LoRA adapter trained on top of the black-forest-labs/FLUX.1-Kontext-dev model to transform images into Avatar-style Na'vi characters, inspired by the visuals from James Cameron's Avatar films.

---

🧠 Model Details

• Base Model: FLUX.1-Kontext-dev (custom diffusion)
• LoRA Rank: 4 / 8 (depending on your version)
• Training Resolution: 1024*1024
• Target Style: Na'vi characters (blue skin, elongated facial features, glowing eyes, etc.)
• Architecture: LoRA fine-tuning with Stable Diffusion compatible UNet blocks.

---

💻 Usage

In Diffusers

from diffusers import StableDiffusionPipeline
from peft import PeftModel
import torch

# Load the base model
pipe = StableDiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", torch_dtype=torch.float16).to("cuda")

# Load the LoRA adapter
pipe.unet.load_attn_procs("your-username/flux-kontext-na-vi-lora")

# Use the model
prompt = "A close-up portrait of a Na'vi warrior in a glowing forest, cinematic lighting"
image = pipe(prompt).images[0]
image.save("output.png")