Arrow2: Image to SVG
Convert a raster image into a clean, editable SVG vector using Arrow 2, taking one image and returning one vector output. The model produces cleaner geometry and stronger composition with fewer control points. Ideal for vectorizing sketches, logos, and line art, or preparing scalable brand and product assets.
Sobre
Arrow2: Image to SVG is a focused ComfyUI workflow that converts a single raster image into a clean, editable SVG vector. It routes your bitmap through LoadImage, vectorizes it with QuiverImageToSVGNode (powered by the Arrow 2 model), and writes the result to disk via SaveSVGNode. The Arrow 2 model is tuned for cleaner geometry and stronger composition, producing fewer control points and more usable paths than traditional auto-tracing.
O que você fornece
- Lendo o fluxo de trabalho
É executado no ComfyUI. Este fluxo de trabalho não pode ser executado nesta página. Abra-o no Comfy Cloud com tudo carregado ou baixe-o para usar no seu próprio ComfyUI.
Experimentar no CloudPerguntas e respostas
High-contrast graphics with clear edges—such as logos, icons, and line art—vectorize best. Photos and gradients can produce many small shapes; simplify or posterize them first for cleaner results.
SaveSVGNode writes the output to your ComfyUI output directory. The exact path is shown in the node’s UI after the run; open that folder to access the .svg file.
Start by improving the input: increase contrast, remove noise, and use solid color regions. You can also resize the image smaller before running. After export, apply path simplification in your vector editor if needed.
Arrow 2 can capture distinct regions as vector shapes. Solid colors and flat graphics are preserved more cleanly than soft gradients. Transparency handling depends on the source; a clean, uniform background yields the best separation.
Workflows relacionados
- ACE-Step
ACE-Step 1.5 Geração de Música (4B LLM)
- Gemini3 Pro Image Preview, Google, Nano Banana Pro
Adicionar cor à ilustração em traço
- Nó parceiro
AI on the Lot 2026 - QwenVL - Aprimorador de Prompt
- Nó parceiro
AI on the Lot 2026 - QwenVL - i2t
- Nó parceiro
AI on the Lot 2026 - WF Final - t2v
- Nó parceiro
AI on the Lot 2026_LTX-2.3_IC LoRA (Union Control)
- Z-Image-Turbo
Alternar nó
- Nó parceiro
Arrow2: Text to SVG
- Seedance 2.0
Captura de Movimento por Profundidade com Seedance 2.0
- Nó parceiro
Colagens em Movimento
- Flux.2 Dev, Flux.2 Klein, GPT-Image-1.5, Grok, Nano Banana Pro, Qwen-Image-Edit, Seedream
Comparação de 1 entrada e múltiplos modelos de edição
- Qwen-Image-Layered
Decomposição de Camadas do Qwen Image Layer para Ilustração v1