Instructions to use Gustavosta/MagicPrompt-Stable-Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gustavosta/MagicPrompt-Stable-Diffusion with Transformers:

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

pipe = pipeline("text-generation", model="Gustavosta/MagicPrompt-Stable-Diffusion")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gustavosta/MagicPrompt-Stable-Diffusion")
model = AutoModelForCausalLM.from_pretrained("Gustavosta/MagicPrompt-Stable-Diffusion")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Gustavosta/MagicPrompt-Stable-Diffusion with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Gustavosta/MagicPrompt-Stable-Diffusion

SGLang

How to use Gustavosta/MagicPrompt-Stable-Diffusion 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 "Gustavosta/MagicPrompt-Stable-Diffusion" \
    --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": "Gustavosta/MagicPrompt-Stable-Diffusion",
		"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 "Gustavosta/MagicPrompt-Stable-Diffusion" \
        --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": "Gustavosta/MagicPrompt-Stable-Diffusion",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Gustavosta/MagicPrompt-Stable-Diffusion with Docker Model Runner:
```
docker model run hf.co/Gustavosta/MagicPrompt-Stable-Diffusion
```

Incorporating it stable-diffusion-webui-Prompt_Generator

by imrayya - opened Jan 14, 2023

Discussion

imrayya

Jan 14, 2023

Hi, I wanted to ask if I have your permission to incorporate the model to an extension I wrote (https://github.com/imrayya/stable-diffusion-webui-Prompt_Generator) for https://github.com/AUTOMATIC1111/stable-diffusion-webui

I will of course give you credit for your model.

Gustavosta

Owner Jan 15, 2023

Hi imrayya!!!

Of course! Anyone is free to use the model and implement it in their project or create a project based on it, as long as they follow the MIT license rules.

imrayya

Jan 15, 2023

Cheers

imrayya changed discussion status to closed Jan 15, 2023

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment