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
```

Tensor size not matching

by hzyang - opened Nov 26, 2025

Discussion

hzyang

Nov 26, 2025

I keep meeting this error when running the script in model card.
Traceback (most recent call last):
File "test_starvec.py", line 22, in
raw_svg = starvector.generate_im2svg(batch, max_length=4000)[0]
File "starvector_arch.py", line 193, in generate_im2svg
return self.model.generate_im2svg(batch, **kwargs)
File "starvector_base.py", line 245, in generate_im2svg
inputs_embeds, attention_mask, prompt_tokens = self._prepare_generation_inputs(
File "starvector_base.py", line 208, in _prepare_generation_inputs
embedded_image = self.image_encoder(image)
File "torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
File "image_encoder.py", line 96, in forward
embeds = self.visual_encoder(image)
File "torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
File "clip_model.py", line 188, in forward
x = x + self.positional_embedding.to(x.dtype)
RuntimeError: The size of tensor a (16) must match the size of tensor b (1024) at non-singleton dimension 2

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