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
import torch

# 1. Realistic Vision modelini yükle
pipeline = AutoPipelineForText2Image.from_pretrained(
    "SG161222/Verus_Vision_1.0b",
    torch_dtype=torch.float16
).to("cuda")

# 2. LoRA'yı zorla yükle (alpha=0.5 ile gücünü azaltın)
pipeline.load_lora_weights(
    "codermert/gamzekocc_fluxx",
    weight_name="lora.safetensors",
    adapter_name="fluxx",
    cross_attention_scale=0.5  # LoRA etkisini hafiflet
)

# 3. Promptta hem trigger hem stil vurgusu yapın
image = pipeline(
    prompt="portrait of TOK, <fluxx>, photorealistic, 8K",  # TOK + adapter_name
    negative_prompt="blurry, deformed"
).images[0]

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