🚀 reddy-v4

reddy-v4 是一个基于 black-forest-labs/FLUX.1-dev 的标准 PEFT LoRA 模型，可用于文本到图像的生成任务。

🚀 快速开始

推理示例

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'Unmapped2895/reddy-v4'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "Realistic wide shot photo of woman posing in a luxurious satin lingerie set, featuring a plunging bra, delicate thong and a classic garter belt with black stockings. The satin lingerie shimmers softly in the light, and the cut emphasizes both sophistication and a hint of allure. The lingerie is detailed with fine lace edges, highlighting her alluring figure. She elegantly styled hair as if getting ready for a formal event. The photo has a cinematic quality with rays of light and dramatic play of shadow and light"


## Optional: quantise the model to save on vram.
## Note: The model was not quantised during training, so it is not necessary to quantise it during inference time.
#from optimum.quanto import quantize, freeze, qint8
#quantize(pipeline.transformer, weights=qint8)
#freeze(pipeline.transformer)
    
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
model_output = pipeline(
    prompt=prompt,
    num_inference_steps=20,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
    width=832,
    height=1216,
    guidance_scale=3.5,
).images[0]

model_output.save("output.png", format="PNG")

✨ 主要特性

• 基于 black-forest-labs/FLUX.1-dev 基础模型构建，属于标准 PEFT LoRA 模型。
• 支持文本到图像、图像到图像等多种生成任务。
• 训练和推理过程中提供了详细的参数设置。

📦 安装指南

文档未提及具体安装步骤，暂不提供。

💻 使用示例

基础用法

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'Unmapped2895/reddy-v4'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "Realistic wide shot photo of woman posing in a luxurious satin lingerie set, featuring a plunging bra, delicate thong and a classic garter belt with black stockings. The satin lingerie shimmers softly in the light, and the cut emphasizes both sophistication and a hint of allure. The lingerie is detailed with fine lace edges, highlighting her alluring figure. She elegantly styled hair as if getting ready for a formal event. The photo has a cinematic quality with rays of light and dramatic play of shadow and light"

pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
model_output = pipeline(
    prompt=prompt,
    num_inference_steps=20,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
    width=832,
    height=1216,
    guidance_scale=3.5,
).images[0]

model_output.save("output.png", format="PNG")

高级用法

文档未提及高级用法示例，暂不提供。

📚 详细文档

验证设置

• CFG：3.5
• CFG Rescale：0.0
• 步数：20
• 采样器：FlowMatchEulerDiscreteScheduler
• 随机种子：42
• 分辨率：832x1216
• 跳过层引导：无

注意：验证设置不一定与训练设置相同。

训练设置

数据集

reddy-v2-512

• 重复次数：10
• 图像总数：13
• 宽高比桶总数：1
• 分辨率：0.262144 兆像素
• 是否裁剪：否
• 裁剪风格：无
• 裁剪宽高比：无
• 是否用作正则化数据：否

reddy-v2-1024

• 重复次数：10
• 图像总数：5
• 宽高比桶总数：1
• 分辨率：1.048576 兆像素
• 是否裁剪：否
• 裁剪风格：无
• 裁剪宽高比：无
• 是否用作正则化数据：否

🔧 技术细节

文本编码器在训练过程中未进行训练，推理时可复用基础模型的文本编码器。

📄 许可证

本项目使用其他许可证。具体许可证信息请参考相关文件。