📦 Liked this? <a target="_blank" rel="ugc" href="https://civarchive.com/user/bazya022020810">Come grab more</a>.🧙‍♀️ <a target="_blank" rel="ugc" href="https://civarchive.com/models/3042299/witcheress-kira-yennefer">Witcheress: Kira / Yennefer</a> — Dark fantasy sorceress cosplay with custom spell effects.V2 <span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);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">An accidental result of a failed cosplay training attempt. Instead of the costume, the model delivered a softer, warmer, and more casual look for Kira. Too good to delete, so here is v2Photorealistic Slavic character LoRA with an aesthetic, soft-realism touch. Balanced for clean skin, natural facial consistency, and zero plastic look.### Quick Settings:* Base Model: Krea 2 Turbo,MOSS* LoRA Weight: 0.8 – 1.0 (recommended: 0.85)* Trigger: None needed (natural character description)* Steps / CFG: 4–8 steps (Turbo workflow), CFG 1.0### Sample Prompt:candid portrait of a woman sitting at an outdoor cafe, holding coffee cup, soft morning light, 50mm lens, natural skin, raw photo

Kira — Photorealistic LoRA [MOSS / Krea 2,Qwen 2.1]

KiraV2Q.safetensors

v2.0 Qwen 2.1

v2.0 Krea 2

v2.0 MOSS

v1.0 Qwen 2.1

v1.0 MOSS

v1.0 Krea 2


# 

## 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：39
* Total training steps：2000
* 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="bazya75/KiraV2Q", origin_file_pattern="KiraV2Q_c1-st2000.safetensors"))

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


KiraV2Q

KiraV2Q_c1-st2000.safetensors

c1-st2000

c1-st1000

Files with SHA256: e447c0da6b8845d418637e09e2a91f1d6eba0a7d7fe87df10760ae713b6f4034