Instructions to use AUTOMATIC/promptgen-majinai-unsafe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AUTOMATIC/promptgen-majinai-unsafe with Transformers:

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

pipe = pipeline("text-generation", model="AUTOMATIC/promptgen-majinai-unsafe")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AUTOMATIC/promptgen-majinai-unsafe")
model = AutoModelForCausalLM.from_pretrained("AUTOMATIC/promptgen-majinai-unsafe", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AUTOMATIC/promptgen-majinai-unsafe with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AUTOMATIC/promptgen-majinai-unsafe

SGLang

How to use AUTOMATIC/promptgen-majinai-unsafe 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 "AUTOMATIC/promptgen-majinai-unsafe" \
    --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": "AUTOMATIC/promptgen-majinai-unsafe",
		"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 "AUTOMATIC/promptgen-majinai-unsafe" \
        --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": "AUTOMATIC/promptgen-majinai-unsafe",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AUTOMATIC/promptgen-majinai-unsafe with Docker Model Runner:
```
docker model run hf.co/AUTOMATIC/promptgen-majinai-unsafe
```

Negative prompt in positive

by jysse - opened Feb 25, 2023

Discussion

jysse

Feb 25, 2023

When used with sd-dynamic-prompts, it add negative prompt in the positive

exemple : 1girl,solo, long hair, light blue hair, blue eyes, cat ears, (hair over one eye:1.2), large breasts, shy smile, cute face, piny skin, solo focus, looking away, happy pose, cum from mouth, cum line, nsfw, shiny new hair, orange vaginal, black nipple, black vaginal wad and white slip or panties as they see fit, shiny gold and amber thighhigh socks and pov, shiny sweat spread between legs, wet towel over your head, shiny hair, blush, Negative prompt: multiple penis, poorly drawn 2girl is too cute, male ejaculation, lowres, 3d girl crying, poorly drawn penis

The negative part is typed in the positive prompt ruining the whole thing

Same thing with Majinai-safe

jysse

Feb 26, 2023

precision : "Don't apply to negative prompts" was checked

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