Instructions to use starvector/starvector-1b-im2svg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use starvector/starvector-1b-im2svg with Transformers:

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

pipe = pipeline("text-generation", model="starvector/starvector-1b-im2svg", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("starvector/starvector-1b-im2svg", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use starvector/starvector-1b-im2svg with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "starvector/starvector-1b-im2svg"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "starvector/starvector-1b-im2svg",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/starvector/starvector-1b-im2svg

SGLang

How to use starvector/starvector-1b-im2svg 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 "starvector/starvector-1b-im2svg" \
    --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": "starvector/starvector-1b-im2svg",
		"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 "starvector/starvector-1b-im2svg" \
        --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": "starvector/starvector-1b-im2svg",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use starvector/starvector-1b-im2svg with Docker Model Runner:
```
docker model run hf.co/starvector/starvector-1b-im2svg
```

I love the concept of having direct text to svg generation.. is there any plan to get it working with newer ComfyUI ?

by toufiqkm - opened Feb 27

Discussion

toufiqkm

Feb 27

I tried a older version of a similar model (OmniSVG) on a Windows PC on very old version of ComfyUI.. it did work extremely well. But it's 2026, Windows 11 has simply became utterly unusable.. so I tried to reinstall that in the very latest version of ComfyUI setup under Linux but that simply didn't work. So I am wondering.. Is there any plan to make StarVector to be more universally accessible so that it can run on ComfyUI regardless of what OS platform (Linux or Mac or Windows) the ComfyUI is installed? like having a single safetensor file ( or it's gguf file adaptation ) that can be stored in standard model storing locations and can use text encoder & VAE from standard encoder & VAE storing locations??

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