Flux Prompt Enhance

🚀 Flux-Prompt-Enhance

Flux-Prompt-Enhance 是一个文本生成模型，它基于 google-t5/t5-base 模型，能够将简短的提示词转化为详细、丰富的文本描述，在文本到文本生成任务中表现出色。

🚀 快速开始

本项目使用 transformers 库实现文本到文本的生成功能。以下是使用该模型的基本步骤：

安装依赖

确保你已经安装了 transformers 库和 torch 库。如果没有安装，可以使用以下命令进行安装：

pip install transformers torch

代码示例

from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

# 模型检查点
model_checkpoint = "gokaygokay/Flux-Prompt-Enhance"

# 分词器
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)

# 模型
model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)

enhancer = pipeline('text2text-generation',
                    model=model,
                    tokenizer=tokenizer,
                    repetition_penalty= 1.2,
                    device=device)

max_target_length = 256
prefix = "enhance prompt: "

short_prompt = "beautiful house with text 'hello'"
answer = enhancer(prefix + short_prompt, max_length=max_target_length)
final_answer = answer[0]['generated_text']
print(final_answer)

# 输出示例：
# a two-story house with white trim, large windows on the second floor,
# three chimneys on the roof, green trees and shrubs in front of the house,
# stone pathway leading to the front door, text on the house reads "hello" in all caps,
# blue sky above, shadows cast by the trees, sunlight creating contrast on the house's facade,
# some plants visible near the bottom right corner, overall warm and serene atmosphere. 

📦 模型信息

📄 许可证

本项目采用 apache-2.0 许可证。