Flux Prompt Enhance

🚀 Flux-Prompt-Enhance

A text2text-generation model based on the Google T5 architecture, designed to enhance short prompts into detailed descriptions.

🚀 Quick Start

This model is a text2text-generation model that can enhance short prompts into detailed descriptions. You can use the following code to quickly start using this model:

from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM

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

# Model checkpoint
model_checkpoint = "gokaygokay/Flux-Prompt-Enhance"

# Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)

# Model
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)

# 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. 

💻 Usage Examples

Basic Usage

from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM

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

# Model checkpoint
model_checkpoint = "gokaygokay/Flux-Prompt-Enhance"

# Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)

# Model
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)

Advanced Usage

# You can adjust parameters such as max_length and repetition_penalty according to your needs to get different enhancement results.
# For example, increasing the max_length can generate more detailed descriptions.
from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM

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

# Model checkpoint
model_checkpoint = "gokaygokay/Flux-Prompt-Enhance"

# Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)

# Model
model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)

enhancer = pipeline('text2text-generation',
                    model=model,
                    tokenizer=tokenizer,
                    repetition_penalty= 1.5,
                    device=device)

max_target_length = 512
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)

📄 License

This project is licensed under the Apache-2.0 license.

📚 Documentation

Model Information