Flux Prompt Enhance

🚀 Flux-Prompt-Enhance

Flux-Prompt-Enhance 是一個文本生成模型，它基於 google-t5/t5-base 模型，能夠將簡短的提示詞轉化為詳細、豐富的文本描述，在文本到文本生成任務中表現出色。

🚀 快速開始

本項目使用 transformers 庫實現文本到文本的生成功能。以下是使用該模型的基本步驟：

安裝依賴

確保你已經安裝了 transformers 庫和 torch 庫。如果沒有安裝，可以使用以下命令進行安裝：

pip install transformers torch

代碼示例

from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
import torch

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

# 模型檢查點
model_checkpoint = "gokaygokay/Flux-Prompt-Enhance"

# 分詞器
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)

# 輸出示例：
# 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

📄 許可證

本項目採用 apache-2.0 許可證。