Instructions to use umm-maybe/image-generator-identifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use umm-maybe/image-generator-identifier with Transformers:

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

pipe = pipeline("image-text-to-text", model="umm-maybe/image-generator-identifier")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("umm-maybe/image-generator-identifier")
model = AutoModelForMultimodalLM.from_pretrained("umm-maybe/image-generator-identifier", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use umm-maybe/image-generator-identifier with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/umm-maybe/image-generator-identifier

SGLang

How to use umm-maybe/image-generator-identifier 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 "umm-maybe/image-generator-identifier" \
    --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": "umm-maybe/image-generator-identifier",
		"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 "umm-maybe/image-generator-identifier" \
        --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": "umm-maybe/image-generator-identifier",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use umm-maybe/image-generator-identifier with Docker Model Runner:
```
docker model run hf.co/umm-maybe/image-generator-identifier
```

image-generator-identifier

Commit History

Nov 2, 2024

21:17
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
2663d90

Oct 16, 2023

03:06
Upload BlipForConditionalGeneration

umm-maybe

25965f0
02:22
Upload 5 files

umm-maybe

11610e2
02:12
Upload BlipForConditionalGeneration

umm-maybe

7c92b39
02:11
initial commit

umm-maybe

858702f

Commit History

Nov 2, 2024

Adding `safetensors` variant of this model⁠

Oct 16, 2023

Upload BlipForConditionalGeneration

Upload 5 files

Upload BlipForConditionalGeneration

initial commit