This is my second object lora training with civision modelscope.I tried to create a Star Trek TNG Phaser Type 2 - circa the 2364s. <a target="_blank" rel="ugc" href="https://memory-alpha.fandom.com/wiki/Type_2_phaser">https://memory-alpha.fandom.com/wiki/Type_2_phaser</a><span style="background-color:rgb(26, 27, 30);color:rgb(141, 141, 143);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Others lora training with different steps in <a target="_blank" rel="ugc" href="https://modelscope.ai/organization/LcarsPicturesDatabase">LCARS Pictures Database Modelscope organization</a>Add to PROMPT:<pre><code>POSE: Subject is standing in a dynamic combat stance holding with right hand a TNGTypeII2364 phaser. The thumb is pressing metal fire button of the phaser. The phaser is pointed to the right.</code></pre><pre><code>(Add for shooting) A bright orange continuous phaser beam is shooting out of the TNGTypeII2364 phaser.</code></pre>Tell me what you think. Every contribution, even the smallest, truly makes a difference. Thank you for everything, even just for reading this introduction.Star Trek ® is a registered trademark of CBS Studios Inc in the United States Patent and Trademark Office, this fan art is not created for profit.

Star Trek TNG Type 2 Phaser

ST-TNG-Type2-Phaser-2364-Qwen-Image-21-v1_c1-st6000.safetensors

Qwen 2.1 - v1

Flux.2 Klein 9B-base - v1

Krea2-Turbo - v1


# 

## 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：13
* Total training steps：6000
* 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="murbytrek/ST-TNG-Type2-Phaser-2364-Qwen-Image-21-v1", origin_file_pattern="ST-TNG-Type2-Phaser-2364-Qwen-Image-21-v1_c1-st6000.safetensors"))

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


Files with SHA256: e423d589dfbad783248e333c6bc45d823393062c2c8d669ad19d0f0dfff889a4