metadata

license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
  - en
tags:
  - flux
  - diffusers
  - lora
  - replicate
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: TOK

Gamzekocc_Fluxx

Trained on Replicate using:

https://replicate.com/ostris/flux-dev-lora-trainer/train

Trigger words

You should use TOK to trigger the image generation.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image, AutoencoderKL
import torch

# 1. Ana modeli yükle
pipeline = AutoPipelineForText2Image.from_pretrained(
    "SG161222/Realistic_Vision_V6.0_B1_noVAE",
    torch_dtype=torch.float16,
    variant="fp16"
).to("cuda")

# 2. VAE ekle (opsiyonel)
pipeline.vae = AutoencoderKL.from_pretrained(
    "stabilityai/sd-vae-ft-mse",
    torch_dtype=torch.float16
).to("cuda")

# 3. LoRA'yı yükle
pipeline.load_lora_weights(
    "codermert/gamzekocc_fluxx",
    weight_name="lora.safetensors",
    adapter_name="fluxx_style"
)

# 4. Görüntü oluştur
image = pipeline(
    prompt="portrait of a cyber ninja, <fluxx_style>, ultra-detailed, 8K",
    negative_prompt="blurry, cartoon, deformed",
    num_inference_steps=30
).images[0]

image.save("cyber_ninja.png")

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers