qwen-image-realism-lora:提升Qwen-Image真实感,增强面部细节、色彩与光影效果

为Qwen-Image模型打造的真实感LoRA,提升面部细节、皮肤纹理、色彩还原与光影效果,支持多场景高质量图像生成,提供ComfyUI工作流。【此简介由AI生成】

分支2Tags0
9b5a5951创建于 2025年8月13日17次提交
文件最后提交记录最后更新时间
Update Realism v1.1 LoRA 🎯 **Key Improvements:** ✅ Facial details are WAY better now - skin textures, fine features ✅ Color accuracy significantly improved ✅ Landscape lighting/shadows look much more natural ✅ Better results across different ethnicities 🖼️ **What it does:** Transforms Qwen-Image outputs to photorealistic quality. Works great for: - Portraits (any ethnicity) - Landscapes - Street photography - Corporate headshots ⚡ **Easy to use:** - ComfyUI workflow included - Works with diffusers - No trigger words - just add "realism" to prompts9 个月前
Update Realism v1.1 LoRA 🎯 **Key Improvements:** ✅ Facial details are WAY better now - skin textures, fine features ✅ Color accuracy significantly improved ✅ Landscape lighting/shadows look much more natural ✅ Better results across different ethnicities 🖼️ **What it does:** Transforms Qwen-Image outputs to photorealistic quality. Works great for: - Portraits (any ethnicity) - Landscapes - Street photography - Corporate headshots ⚡ **Easy to use:** - ComfyUI workflow included - Works with diffusers - No trigger words - just add "realism" to prompts9 个月前
Update README.md (#4) - Update README.md (879cc36a2b33801ccc8744e6eb117e23650758a3) Co-authored-by: Aritra Roy Gosthipaty <ariG23498@users.noreply.huggingface.co> 9 个月前
Update Realism v1.1 LoRA 🎯 **Key Improvements:** ✅ Facial details are WAY better now - skin textures, fine features ✅ Color accuracy significantly improved ✅ Landscape lighting/shadows look much more natural ✅ Better results across different ethnicities 🖼️ **What it does:** Transforms Qwen-Image outputs to photorealistic quality. Works great for: - Portraits (any ethnicity) - Landscapes - Street photography - Corporate headshots ⚡ **Easy to use:** - ComfyUI workflow included - Works with diffusers - No trigger words - just add "realism" to prompts9 个月前

license: apache-2.0 language:

  • en base_model:
  • Qwen/Qwen-Image pipeline_tag: text-to-image tags:
  • lora
  • qwen
  • qwen-image
  • realism
  • realism-lora library_name: diffusers

LORA Qwen-Image 示例

适用于 Qwen-Image 的 Lora

需包含 Realism 一词

📝 更新日志

2025年8月13日 - Realism v1.1 版本发布

  • 增强面部细节质量:优化精细面部特征及皮肤纹理渲染效果
  • 提升色彩还原度:全场景色彩表现更精准、更鲜明
  • 改进风景光影效果:增强户外场景自然光照效果及阴影细节
  • 增加不同 ethnicity 多样性:优化各 racial 和 ethnic 特征的呈现效果与质量

🧪 使用方法


🔧 初始化

from diffusers import DiffusionPipeline
import torch

model_name = "Qwen/Qwen-Image"

# Load the pipeline
if torch.cuda.is_available():
    torch_dtype = torch.bfloat16
    device = "cuda"
else:
    torch_dtype = torch.float32
    device = "cpu"

pipe = DiffusionPipeline.from_pretrained(model_name, torch_dtype=torch_dtype)
pipe = pipe.to(device)

🔌 加载 LoRA 权重

# Load LoRA weights
pipe.load_lora_weights('flymy_realism.safetensors', adapter_name="lora")

🎨 使用基于人物训练的 lora 生成图像

prompt = '''Super Realism portrait of a teenager woman of African descent, serene calmness, arms crossed, illuminated by dramatic studio lighting, sunlit park in the background, adorned with delicate jewelry, three-quarter view, sun-kissed skin with natural imperfections, loose shoulder-length curls, slightly squinting eyes, environmental street portrait with text "FLYMY AI" on t-shirt.'''
negative_prompt =  " "
image = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=1024,
    height=1024,
    num_inference_steps=50,
    true_cfg_scale=5,
    generator=torch.Generator(device="cuda").manual_seed(346346)
)

# Display the image (in Jupyter or save to file)
image.show()
# or
image.save("output.png")

🖼️ 示例输出

Sample Output

🎛️ 与 ComfyUI 配合使用

我们提供了一个即用型 ComfyUI 工作流,可与我们训练的 LoRA 模型配合使用。按照以下步骤设置和使用该工作流:

设置说明

  1. 下载最新版 ComfyUI

  2. 安装 ComfyUI

    • 按照 ComfyUI 仓库 中的安装说明进行操作
    • 确保所有依赖项均已正确安装
  3. 下载 Qwen-Image 模型权重

  4. 将 Qwen-Image 权重放置到 ComfyUI 中

    • 将下载的 Qwen-Image 模型文件复制到 ComfyUI/models/ 中的相应文件夹
    • 按照模型仓库中指定的文件夹结构进行操作
  5. 下载我们的预训练 LoRA 权重

  6. 将 LoRA 权重放置到 ComfyUI 中

    • 将 LoRA 文件 flymy-ai/qwen-image-lora/pytorch_lora_weights.safetensors 复制到 ComfyUI/models/loras/
  7. 加载工作流

    • 在浏览器中打开 ComfyUI
    • 加载此仓库中的工作流文件 qwen_image_lora_example.json
    • 该工作流已预先配置,可与我们的 LoRA 模型配合使用

工作流特点

  • ✅ 预先配置用于 Qwen-Image + LoRA 推理
  • ✅ 优化设置以获得最佳质量输出
  • ✅ 轻松调整提示词和参数
  • ✅ 与我们所有训练的 LoRA 模型兼容

ComfyUI 工作流提供了一个用户友好的界面,无需编写 Python 代码即可使用我们训练的 LoRA 模型生成图像。

🖼️ 工作流截图

ComfyUI Workflow

📊 并排对比

以下是展示我们的 LoRA 模型在不同场景下改进效果的对比图片:

山地景观

提示词"realism, mountain landscape at golden hour, low sun grazing alpine meadows, crisp ridgelines, thin mist in valley, high dynamic range sky, 24mm f/8, ISO 100, tripod, ultra-sharp foreground grass, micro-contrast on rocks"

山地景观对比

雨夜城市场景

提示词"realism, rainy night city scene with neon reflections, person holding a transparent umbrella, water droplets sharp on umbrella surface, shallow DOF, 55mm f/1.8, ISO 1600, blue and magenta neon, storefront sign reads "OPEN 24/7""

雨夜城市对比

运动动态

提示词"realism, athlete mid-sprint on track, strong sunlight, backlit dust particles, frozen motion at 1/2000s, 200mm f/2.8, ISO 400, muscle definition and sweat droplets detailed, stadium banner says "FINALS""

运动动态对比

企业肖像

提示词"realism, corporate headshot of a CTO in glass-walled office, city skyline bokeh, balanced key/fill lighting, 85mm f/2, ISO 100, crisp lapel and hair detail, subtle reflection on glasses"

企业肖像对比

🤝 支持

如有任何问题或建议,欢迎加入我们的社区:

⭐ 如果您喜欢本项目,请不要忘记给仓库点赞!


license: apache-2.0

项目介绍

为Qwen-Image模型打造的真实感LoRA,提升面部细节、皮肤纹理、色彩还原与光影效果,支持多场景高质量图像生成,提供ComfyUI工作流。【此简介由AI生成】

定制我的领域

下载使用量

0

项目总下载次数(含Clone、Pull、 zip 包及 release 下载),每日凌晨更新