<h1 id="viviluxe">ViviLuxe 🖤</h1><h3 id="vivi-is-trained-on-flux.1-supernova.-use-with-the-flux-family-of-models-for-maximum-compatibility.">Vivi is trained on Flux.1 Supernova. Use with the Flux family of models for maximum compatibility.</h3><h2 id="positive-prompt:">Positive Prompt:</h2>&lt;instant&gt; hyper realistic instagram influencer with long hair wearing gym clothes, 28 years old, viviluxe, 100mm lens, canon, HDR, beautiful, 8k<h2 id="negative-prompt:">Negative Prompt:</h2>blurry, bad quality, noisy, grainy, deformed (keep this simple it works better)<h2 id="settings:">Settings:</h2>CFG: 4Strength: 0.4-0.5Sampler" DPM 2 ++ KarrasTrigger: "instant"Upscaler: 4x Ultra Sharp or Real ESRGAN<h2 id="support-tensorvizion-or-ai-resources-and-freebies:">Support TensorVizion | AI Resources &amp; Freebies:</h2>KoFI: <a target="_blank" rel="ugc" href="https://www.kofi.com/tensorvizion">https://www.kofi.com/tensorvizion</a>Patreon: <a target="_blank" rel="ugc" href="https://www.patreon.com/tensorvizion">https://www.patreon.com/tensorvizion</a><h2 id="deploy-this-model-and-much-more:">Deploy this Model and much more:</h2><a target="_blank" rel="ugc" href="https://runpod.io?ref=1jcw9158">https://runpod.io?ref=1jcw9158</a>

ViviLuxe

ViviLuxe-Qwen-2.1_c1-st4000.safetensors

Qwen Image 2.1

Flux.2

Jib Mix(SD-1.5)

Flux 1 Dev


# 

## Model Introduction

This model is trained using the [Civision/model training](https://modelscope.ai/civision/modelTraining) environment and computing resources provided by ModelScope.

* Model Type: LoRA
* Base Model: [Qwen/Qwen-Image-2.1](https://modelscope.ai/models/Qwen/Qwen-Image-2.1)
* Training Code: [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* Data amount：26
* Total training steps：4000
* License: Apache-2.0

## Inference Code

Install [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio):

```bash
pip install diffsynth
```

Inference:

```python
from diffsynth.pipelines.qwen_image_21 import QwenImage21Pipeline, ModelConfig
import torch

pipe = QwenImage21Pipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="text_encoder/model*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="vae/diffusion_pytorch_model*.safetensors"),
    ],
    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="processor/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="tensorvizion/ViviLuxe-Qwen-2.1", origin_file_pattern="ViviLuxe-Qwen-2.1_c1-st4000.safetensors"))

prompt = "a cat"
image = pipe(prompt, seed=0, num_inference_steps=50)
image.save("image.png")
```


Files with SHA256: a034b78cdc9965f1eeec6d9b60f96ebd02c28c29b35c019fa4ddd67c16f8c1d3