---
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
# widget:
#   - text: >-
#       prompt
#     output:
#       url: https://...
instance_prompt: TOK
---

# Gamzekocc_Fluxx

<Gallery />

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](https://github.com/huggingface/diffusers)

```py
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](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)