Arrow2: Text to SVG
Generate editable SVG vector graphics directly from text prompts using Arrow 2, producing one image output with no file inputs required. Ideal for illustrations, technical diagrams, logo design, and turning written briefs into clean, scalable vector assets.
정보
Arrow2: Text to SVG is a focused ComfyUI workflow that converts natural-language prompts into clean, editable vector graphics. It uses QuiverTextToSVGNode to send your prompt to the Arrow 2 text-to-vector model and receive raw SVG markup, then hands that SVG string to SaveSVGNode to write a single .svg file to disk—no image inputs required. Because the output is true SVG, it scales cleanly at any size and is easy to edit in tools like Figma, Illustrator, or Inkscape.
제공할 항목
- 워크플로 읽는 중
ComfyUI에서 실행됩니다. 이 워크플로는 이 페이지에서 실행할 수 없습니다. 모든 항목이 로드된 Comfy Cloud에서 열거나, 자체 ComfyUI에서 사용하려면 다운로드하세요.
Cloud에서 사용해 보기질문과 답변
If your QuiverTextToSVGNode is configured to call an external Arrow 2 API, you’ll need to supply the required credentials (API key or endpoint) in the node settings or environment. Refer to the node’s documentation for the exact configuration method used in your setup.
Yes. The node returns standard SVG markup (paths and shapes), so the result is fully vector and resolution-independent. You can scale it by editing the width/height or viewBox attributes in the SVG or by resizing directly in your vector editor.
Include specific instructions in your prompt, such as a limited palette with hex codes (e.g., “#111111 and #FF5A5F only”), stroke vs. fill preferences, stroke width, and geometric or rounded aesthetics. You can also fine-tune these later in your vector editor since fills, strokes, and paths are editable.
Ask for simpler geometry in your prompt (e.g., “minimal paths, few anchor points, no gradients”). After generation, you can further optimize with tools like SVGO or your editor’s path-simplify features to reduce node counts and file size.
관련 워크플로
- Flux.2 Dev, Flux.2 Klein, GPT-Image-1.5, Grok, Nano Banana Pro, Qwen-Image-Edit, Seedream
1개 입력 및 다중 편집 모델 비교
- ACE-Step
ACE-Step 1.5 음악 생성 (4B LLM)
- 파트너 노드
AI on the Lot 2026 - Final WF - t2v
- 파트너 노드
AI on the Lot 2026 - QwenVL - i2t
- 파트너 노드
AI on the Lot 2026 - QwenVL - 프롬프트 강화
- 파트너 노드
AI on the Lot 2026_LTX-2.3_IC LoRA (Union Control)
- 파트너 노드
Arrow2: Image to SVG
- Seedance 2.0
Depth Motion Capture with Seedance 2.0
- ElevenLabs
ElevenLabs: 음성에서 텍스트로
- 파트너 노드
Fish Audio: Speech to Text
- Flux.1, Flux
Flux.1 Canny 모델
- Flux.1, Flux
Flux.1 Redux 모델