Instructions to use Hatman/Flux-Prompt-Enhance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hatman/Flux-Prompt-Enhance with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Hatman/Flux-Prompt-Enhance")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Hatman/Flux-Prompt-Enhance")
model = AutoModelForSeq2SeqLM.from_pretrained("Hatman/Flux-Prompt-Enhance")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Hatman/Flux-Prompt-Enhance with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hatman/Flux-Prompt-Enhance"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hatman/Flux-Prompt-Enhance",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Hatman/Flux-Prompt-Enhance

SGLang

How to use Hatman/Flux-Prompt-Enhance with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Hatman/Flux-Prompt-Enhance" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hatman/Flux-Prompt-Enhance",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Hatman/Flux-Prompt-Enhance" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hatman/Flux-Prompt-Enhance",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Hatman/Flux-Prompt-Enhance with Docker Model Runner:
```
docker model run hf.co/Hatman/Flux-Prompt-Enhance
```

HatmanStack commited on Jan 31, 2025

Commit

c8d5c42

1 Parent(s): 4b05d70

checkpoint

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ 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)
@@ -58,7 +58,7 @@ class PromptEnhancer:
         self.device = "cuda" if torch.cuda.is_available() else "cpu"
         # Model checkpoint
-        self.model_checkpoint = "gokaygokay/Flux-Prompt-Enhance"
         # Tokenizer and Model
         self.tokenizer = AutoTokenizer.from_pretrained(self.model_checkpoint)

 device = "cuda" if torch.cuda.is_available() else "cpu"
 # Model checkpoint
+model_checkpoint = "Hatman/Flux-Prompt-Enhance"
 # Tokenizer
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
         self.device = "cuda" if torch.cuda.is_available() else "cpu"
         # Model checkpoint
+        self.model_checkpoint = "Hatman/Flux-Prompt-Enhance"
         # Tokenizer and Model
         self.tokenizer = AutoTokenizer.from_pretrained(self.model_checkpoint)