Instructions to use RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits with Transformers:

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

pipe = pipeline("text-generation", model="RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits

SGLang

How to use RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits 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 "RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits" \
    --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": "RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits",
		"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 "RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits" \
        --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": "RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/Gustavosta_-_MagicPrompt-Stable-Diffusion-8bits
```

RichardErkhov commited on May 3, 2024

Commit

ad36f80

verified ·

1 Parent(s): 374c3b3

uploaded readme

Browse files

Files changed (1) hide show

README.md +48 -0

README.md ADDED Viewed

	@@ -0,0 +1,48 @@

+Quantization made by Richard Erkhov.
+[Github](https://github.com/RichardErkhov)
+[Discord](https://discord.gg/pvy7H8DZMG)
+[Request more models](https://github.com/RichardErkhov/quant_request)
+MagicPrompt-Stable-Diffusion - bnb 8bits
+- Model creator: https://huggingface.co/Gustavosta/
+- Original model: https://huggingface.co/Gustavosta/MagicPrompt-Stable-Diffusion/
+Original model description:
+---
+license: mit
+---
+# MagicPrompt - Stable Diffusion
+This is a model from the MagicPrompt series of models, which are [GPT-2](https://huggingface.co/gpt2) models intended to generate prompt texts for imaging AIs, in this case: [Stable Diffusion](https://huggingface.co/CompVis/stable-diffusion).
+## 🖼️ Here's an example:
+<img src="https://files.catbox.moe/ac3jq7.png">
+This model was trained with 150,000 steps and a set of about 80,000 data filtered and extracted from the image finder for Stable Diffusion: "[Lexica.art](https://lexica.art/)". It was a little difficult to extract the data, since the search engine still doesn't have a public API without being protected by cloudflare, but if you want to take a look at the original dataset, you can have a look here: [datasets/Gustavosta/Stable-Diffusion-Prompts](https://huggingface.co/datasets/Gustavosta/Stable-Diffusion-Prompts).
+If you want to test the model with a demo, you can go to: "[spaces/Gustavosta/MagicPrompt-Stable-Diffusion](https://huggingface.co/spaces/Gustavosta/MagicPrompt-Stable-Diffusion)".
+## 💻 You can see other MagicPrompt models:
+- For Dall-E 2: [Gustavosta/MagicPrompt-Dalle](https://huggingface.co/Gustavosta/MagicPrompt-Dalle)
+- For Midjourney: [Gustavosta/MagicPrompt-Midourney](https://huggingface.co/Gustavosta/MagicPrompt-Midjourney) **[⚠️ In progress]**
+- MagicPrompt full: [Gustavosta/MagicPrompt](https://huggingface.co/Gustavosta/MagicPrompt) **[⚠️ In progress]**
+## ⚖️ Licence:
+[MIT](https://huggingface.co/models?license=license:mit)
+When using this model, please credit: [Gustavosta](https://huggingface.co/Gustavosta)
+**Thanks for reading this far! :)**