AUTOMATIC1111: Build a Custom Sketch-to-Image API

ThatPainter is reader-supported. When you buy through links on our site, we may earn an affiliate commission. Learn More

Yes—AUTOMATIC1111 can power a custom sketch-to-image API, but it is not itself a hosted commercial API. It is an open-source Stable Diffusion web interface that can expose a local HTTP API when started with --api. For a basic workflow, send a base64-encoded sketch to POST /sdapi/v1/img2img. If preserving the sketch’s pose, silhouette, or layout matters, add ControlNet with Scribble, Lineart, Canny, or another suitable structural model.

The practical production design is a client-facing backend in front of a private AUTOMATIC1111 process—not an unauthenticated port 7860 exposed to the internet.

#	Preview	Product	Price
1		Wacom Intuos Small, Wired Graphic Drawing Tablet with Pen + Software	$39.95	Buy on Amazon
2		XPPen Deco 01 V3 10x6 Drawing Tablet, 16K Battery-Free Stylus, 8 Keys	$45.00	Buy on Amazon
3		HUION Inspiroy H640P 6x4 inch Drawing Tablet 8192 Pen Pressure	$29.99	Buy on Amazon
4		4 Pack LCD Writing Tablet for Kids, 8.5 Inch Colorful Doodle Board Drawing Tablet, Educational...	$9.99	Buy on Amazon
5		XPPen Artist 13.3 Pro V2 Drawing Tablet with Screen, 16K, Full-Laminated	$211.00	Buy on Amazon

As an Amazon Associate I earn from qualifying purchases.

What you are actually building

AUTOMATIC1111 Stable Diffusion WebUI is an open-source interface and inference server supporting text-to-image, image-to-image, inpainting, outpainting, model selection, LoRAs, and extensions such as ControlNet. Its API is an interface to a running WebUI process, not a vendor-operated endpoint with guaranteed uptime, billing, autoscaling, or a fixed public URL.

The basic architecture looks like this:

Client
  ↓
Your backend API
  ↓
Authentication, validation, queue, rate limits
  ↓
Private AUTOMATIC1111 instance
  ↓
GPU inference
  ↓
Image response or object storage

For the project and API documentation, see the AUTOMATIC1111 repository and its API guide.

#1 Best Overall

Wacom Intuos Small, Wired Graphic Drawing Tablet with Pen + Software

• Wacom Intuos Small Graphics Drawing Tablet: Enjoy industry leading tablet performance in superior control and precision with Wacom's EMR, battery free technology that feels like pen on paper
• Works With All Software: Wacom Intuos tablet can be used in any software program to explore new facets of digital creativity; draw, paint, edit photos/videos, create designs, and mark up documents
• What the Professionals Use: Wacom's industry leading pen technology and pen to paper feeling makes it the preferred drawing tablet of professional graphic designers
• Software and Training Included: Only Wacom gives you software with every purchase. Register your Intuos tablet and gain access to some of the best creative software and Wacom's online training
• Wacom is the Global Leader in Drawing Tablet and Displays: For over 40 years in pen display and tablet market, you can trust that Wacom to help you bring your vision, ideas and creativity to life

$39.95

Buy on Amazon

Three different sketch workflows

“Sketch-to-image” can describe three related but different operations:

1. Native img2img: a rough raster sketch is supplied as the initial image. Diffusion reinterprets it according to the prompt.
2. ControlNet guidance: the sketch is supplied as structural conditioning. This generally gives stronger control over contours, pose, or composition.
3. Inpainting: a sketch and mask are used to generate or alter only selected parts of an existing image.

Native img2img is the easiest implementation. It is also the least reliable for exact geometry. ControlNet does not copy a sketch pixel-for-pixel; it guides generation through an additional spatial condition.

Prerequisites

• A working AUTOMATIC1111 installation.
• A compatible Stable Diffusion checkpoint, such as an SD 1.5- or SDXL-family model.
• A GPU with enough memory for the selected model, resolution, batch size, and optional ControlNet units.
• A sketch in PNG, JPEG, or WebP format.
• Python with the requests and Pillow packages for the example below.
• Optionally, the ControlNet extension and a ControlNet model compatible with the checkpoint family.

There is no universal VRAM requirement. Memory use changes substantially with model family, output size, batch size, attention optimizations, and the number of ControlNet units. If you do not have suitable hardware, a rented GPU such as a RunPod Pod or a marketplace instance from Vast.ai can host the software. Their current rates vary by GPU, deployment type, location, supply, demand, storage, and bandwidth; consult the RunPod pricing documentation and Vast.ai pricing documentation rather than relying on fixed hourly figures.

Enable and verify the AUTOMATIC1111 API

Start the WebUI with the API flag. On Linux or macOS:

./webui.sh --api

On Windows, add the flag to webui-user.bat, commonly through:

set COMMANDLINE_ARGS=--api

A headless deployment may use:

./webui.sh --api --nowebui

Available flags can vary by build, so confirm them in the installed version. Do not assume that a command copied from another fork or old tutorial applies unchanged.

Rank #2

Sale

XPPen Deco 01 V3 10x6 Drawing Tablet, 16K Battery-Free Stylus, 8 Keys

• Word-first 16K Pressure Levels: The upgraded stylus features 16,384 levels of pressure sensitivity and supports up to 60 degrees of tilt, delivering smoother lines and shading for a natural drawing experience. With no battery or charging needed, it operates like a real pen, making it easy for beginners to create effortlessly. This functionality helps novice artists develop their skills and explore their creativity without the intimidation of complex tools
• Designed for Beginners: This drawing pad desinged with 8 customizable shortcuts for both right and left-hand users, express keys create a highly ergonomic and convenient work platform
• Perfectly Adapted for Android: The XPPen Deco 01 V3 art tablet supports connections with Android devices running version 10.0 and above. It is recommended to download the XPPen Tools Android application, which adapts to your smartphone's screen aspect ratio, ensuring accurate mapping. It also supports mapping on Android screens with different aspect ratios in portrait mode
• Large Drawing Space, Bigger Bold Inspiration: This expansive drawing pad has10 x 6.25-inch helps you break through the limit between shortcut keys and drawing area
• Easy Connectivity for Beginners: The Deco 01 V3 offers USB-C to USB-C connectivity, plus adapters for USB C. This ensures easy connection to various devices, allowing beginner artists to set up quickly and focus on their creativity without compatibility concerns. Whether using a laptop, tablet, or desktop, the Deco 01 V3 provides a seamless experience, making it an ideal choice for those just starting their digital art journey

$45.00

Buy on Amazon

Once the server is running, inspect the live OpenAPI documentation at:

http://127.0.0.1:7860/docs

That runtime schema is especially important for extension fields. The AUTOMATIC1111 wiki notes that its API guide may be outdated and directs users to the running /docs endpoint as the more authoritative description of the installed server.

Test connectivity with:

curl http://127.0.0.1:7860/sdapi/v1/samplers

A successful response should contain the available samplers. The default address and port may differ if the instance was configured otherwise.

Native img2img: the simplest sketch API

The core endpoint is:

POST http://127.0.0.1:7860/sdapi/v1/img2img

The sketch is sent in the init_images array as a base64-encoded image. Important request fields include:

A useful initial denoising range for a recognizable composition is roughly 0.35–0.60, but this is a tuning range, not a rule. Lower values preserve more of the source and higher values permit more reinterpretation. The right setting depends on the sketch, model, prompt, dimensions, and whether ControlNet is also active.

Working Python example

import base64
import json
from pathlib import Path

import requests

A1111_URL = "http://127.0.0.1:7860"
SKETCH_PATH = Path("sketch.png")
OUTPUT_PATH = Path("generated.png")


def image_to_base64(path: Path) -> str:
    return base64.b64encode(path.read_bytes()).decode("utf-8")


def save_base64_image(encoded: str, path: Path) -> None:
    path.write_bytes(base64.b64decode(encoded))


payload = {
    "init_images": [image_to_base64(SKETCH_PATH)],
    "prompt": (
        "a cinematic digital painting of a small cabin beside a lake, "
        "pine forest, atmospheric lighting, detailed environment"
    ),
    "negative_prompt": (
        "blurry, distorted geometry, duplicate objects, malformed details, "
        "watermark, text"
    ),
    "denoising_strength": 0.50,
    "steps": 25,
    "cfg_scale": 7,
    "width": 768,
    "height": 768,
    "seed": 123456789,
    "batch_size": 1,
    "n_iter": 1,
}

response = requests.post(
    f"{A1111_URL}/sdapi/v1/img2img",
    json=payload,
    timeout=300,
)
response.raise_for_status()
result = response.json()

if not result.get("images"):
    raise RuntimeError(f"No image returned: {json.dumps(result, indent=2)}")

save_base64_image(result["images"][0], OUTPUT_PATH)
print(f"Saved {OUTPUT_PATH}")

Install the client dependencies if necessary:

pip install requests pillow

A successful response normally contains an images array. Each item is an encoded image string. Depending on settings and version, the response may also contain generation information and parameters. The API returns encoded image data; your client decides how to decode and store it.

Rank #3

Sale

HUION Inspiroy H640P 6x4 inch Drawing Tablet 8192 Pen Pressure

• Customize Your Workflow: The 6 customizable press keys on Huion H640P drawing tablet for pc let you assign your most-used commands—like undo, zoom, brush switch, or save—so you can keep your hands on the tablet and your mind on the art. Whether you're a digital painter switching brushes, or a comic artist zooming in and out, these keys keep your workflow smooth and uninterrupted. Plus, the Huion driver lets you save different shortcut profiles for different apps, so you never have to reconfigure when switching software.
• Professional Pen Performance: Huion H640P drawing pad for computer comes with the battery-free PW100 stylus that's always ready when inspiration strikes. With 8192 levels of pressure sensitivity, every light sketch, or bold stroke responds naturally to your hand—just like a real pen. The 5080 LPI resolution and 233 PPS report rate deliver lag-free, precise strokes, so you can draw confidently without second-guessing your cursor. The pen side buttons help you switch between pen and eraser instantly.
• Compact and Portable: Huion H640P computer graphics tablet features a compact, ultra-portable design at just 0.3 inches thin and 0.61 lbs light, so it slides easily into your backpack—perfect for sketching in coffee shops, taking notes in class, or editing on the go between home and studio. The 6x4 inch active area offers enough room for natural pen movements while fitting comfortably on crowded desks, or lecture hall seats.
• Stable Compatibility: Huion H640P graphic drawing tablet works seamlessly with Mac, Windows, Linux PCs, and Android smartphones/tablets (OS version 6.0 or later). Left-handed friendly, and you just need to flip the tablet and adjust the settings in the driver. Please note: H640P does NOT support iPhone/iPad.
• Move Beyond the Mouse: Huion Inspiroy H640P is a pen tablet that replaces your mouse for more natural, precise control. Freehand draw, take notes, or even play OSU—everything you do with a mouse, you can do better with a pen. The precise tip makes it ideal for detailed photo editing, graphic design, or signing PDF. Meanwhile, the ergonomic pen grip helps you avoid the strain that comes from hours of using a mouse.

$29.99

Buy on Amazon

Reproducibility is not determinism

Saving a seed is useful, but a seed alone does not guarantee identical output. For meaningful reproduction, preserve the checkpoint, VAE, prompt, negative prompt, seed, sampler, scheduler where applicable, dimensions, denoising strength, ControlNet model and settings, extension versions, and relevant runtime configuration.

Results can change after updating the model, VAE, AUTOMATIC1111, ControlNet, Python dependencies, GPU drivers, or hardware execution path. Treat the complete generation configuration as the reproducibility record.

Improve structural fidelity with ControlNet

Native img2img can alter object placement, silhouette, perspective, relative scale, limb arrangement, and negative space—particularly when the sketch is sparse or low contrast. ControlNet adds a conditioning pathway for spatial information such as edges, depth, pose, and segmentation.

ControlNet is not an automatic sketch interpreter. Results depend on line thickness, contrast, background color, preprocessing, conditioning weight, model compatibility, and the prompt.

Version-sensitive ControlNet payload

Current ControlNet integrations generally place ControlNet data in the standard /sdapi/v1/img2img or /sdapi/v1/txt2img request through an always-on script. Older tutorials may use dedicated routes such as /controlnet/img2img. Payloads, model names, preprocessor names, and field shapes can vary by extension release.

A representative structure is:

{
  "init_images": ["BASE64_SKETCH"],
  "prompt": "a finished fantasy castle illustration",
  "negative_prompt": "blurry, malformed, text, watermark",
  "denoising_strength": 0.55,
  "steps": 30,
  "cfg_scale": 7,
  "alwayson_scripts": {
    "ControlNet": {
      "args": [
        {
          "enabled": true,
          "input_image": "BASE64_SKETCH",
          "module": "scribble",
          "model": "CONTROLNET_MODEL_NAME",
          "weight": 0.8,
          "resize_mode": "Crop and Resize",
          "guidance_start": 0.0,
          "guidance_end": 1.0
        }
      ]
    }
  }
}

Do not treat this as a guaranteed drop-in request. First configure one successful generation in the AUTOMATIC1111 UI, inspect the live /docs schema and the installed ControlNet API documentation, then compare the browser request or generated API payload with your code.

Rank #4

4 Pack LCD Writing Tablet for Kids, 8.5 Inch Colorful Doodle Board Drawing Tablet, Educational Learning Toys Birthday Gifts for Boys Girls Age 3 4 5 6 7 8

• 4 Pack for More Fun: Apply the newest flexible liquid crystal technology, brighter and clearer than most LCD writing tablet. Take pressure-sensitive technology, you can draw lines of different thicknesses through different pressure levels. Package includes 4 pack lcd writing tablet (Blue, Light blue, Green and Pink), free children's imagination and creativity.
• 8.5 Inch Colorful Lcd writing Tablet: TQU kids LCD doodle board is a creative education and learning toy, perfect support for drawing, writing, spelling, math, remark, and notes which can let your kids freely release their natural instincts. With erase button on the front and lock switch. You can draw and erase easily by pressing the button on the front of the board. The pen fits snug on top of tablet and it will not come loose.
• Easy to use and Durable: The LCD writing tablet for kids is easy to use, just use the stylus to write, draw, scribble, doodle anything you want. Press the erase button to clear the screen in one second. Or press the lock key to save the screen contents. Our magic reusable drawing tablet is built in a button battery.
• Safe & Portable Toddler Travel Toys: Great for quiet, take-along entertainment. It’s an easy way to color on the go without lugging a bunch of stuff in the car or to a restaurant or church.
• Perfect Gift Idea: The multi-functional LCD writing tablet is a great gift choice for kids. It can be an educational toy for preschoolers. A perfect parent-pick gift for 3 4 5 6 7 8 year old girls and boys on back to school, homeschool, birthday, Easter, Children's Day, Thanksgiving Day, Christmas and any occasion.

$9.99

Buy on Amazon

Native img2img is usually preferable when some variation is welcome and implementation simplicity matters. Choose ControlNet when the exact pose, silhouette, layout, or repeated composition is important.

Image preparation and aspect ratio

Resize policy

If sketch and output dimensions differ, the service may crop, stretch, or pad the source according to resize_mode. This can remove important edges or distort geometry. Choose deliberately:

• Crop and resize: fills the target canvas but may cut off the sketch.
• Resize and pad: preserves the whole sketch but may introduce borders.
• External preprocessing: resize and pad before submission for predictable results.

For user-generated images, do not pass arbitrary dimensions directly to the GPU. Normalize dimensions to approved sizes and limit the maximum pixel count.

Transparency and line polarity

Transparent PNGs may produce inconsistent results because alpha compositing and preprocessing differ between workflows. Flatten the sketch onto an explicit background when consistency matters.

If a black-on-white sketch produces weak or inverted conditioning:

1. Inspect the preprocessed control image.
2. Invert the sketch if necessary.
3. Increase contrast.
4. Remove faint gray noise.
5. Try another preprocessor.

Put a backend in front of A1111

A public application should not send browser requests directly to an exposed AUTOMATIC1111 port. Your backend should authenticate users, validate files, limit resource use, queue jobs, and decide what results are retained.

Best Value

Sale

XPPen Artist 13.3 Pro V2 Drawing Tablet with Screen, 16K, Full-Laminated

• PLEASE NOTE：XPPen Artist13.3 Pro drawing tablet Need to connect with computer,you need to use it with your computer or laptop, the 3 in 1 cable is included
• Drawing Tablet with Screen: Tilt Function- XPPen Artist 13.3 Pro supports up to 60 degrees of tilt function, so now you don't need to adjust the brush direction in the software again and again. Simply tilt to add shading to your creation and enjoy smoother and more natural transitions between lines and strokes
• Graphics Tablets: High Color Gamut- The 13.3 inch fully-laminated FHD Display pairs a superb color accuracy of 88% NTSC (Adobe RGB≧91%，sRGB≧123%) with a 178-degree viewing angle and delivers rich colors, vivid images, and dazzling details in a wider view. Your creative world is now as powerful as it is colorful
• Drawing Pad: One is enough- The sleek Red Dial on the display is expertly designed with creators in mind, its strategic placement allows for natural drawing postures. With just one wheel, you can effortlessly zoom in and out, adjust brush sizes, and flip the canvas—all tailored to suit the habits of everyday artists. The 8 customizable shortcut keys allow you to personalize your setup, streamlining your workflow and enhancing creative efficiency
• Universal Compatibility & Software Support：supports Windows 7 (or later), Mac OS X 10.10 (or later), Chrome OS 88 (or later), and Linux systems. Fully compatible with major creative software including Photoshop, Illustrator, SAI, and Blender 3D. Register your device to access additional programs like ArtRage 5 and openCanvas for expanded creative possibilities.

$211.00

Buy on Amazon

Reference FastAPI wrapper

import base64
import io
import os

import requests
from fastapi import FastAPI, File, Form, HTTPException, UploadFile
from fastapi.responses import Response
from PIL import Image

app = FastAPI()
A1111_URL = os.getenv("A1111_URL", "http://127.0.0.1:7860")

@app.post("/generate")
async def generate(
    sketch: UploadFile = File(...),
    prompt: str = Form(...),
    negative_prompt: str = Form(""),
    denoising_strength: float = Form(0.5),
):
    if sketch.content_type not in {"image/png", "image/jpeg", "image/webp"}:
        raise HTTPException(415, "Use PNG, JPEG, or WebP")

    if not 0.0 <= denoising_strength <= 1.0:
        raise HTTPException(400, "denoising_strength must be between 0 and 1")

    raw = await sketch.read()

    try:
        image = Image.open(io.BytesIO(raw))
        image.load()
    except Exception:
        raise HTTPException(400, "Invalid image")

    if image.width > 2048 or image.height > 2048:
        raise HTTPException(413, "Image is too large")

    encoded = base64.b64encode(raw).decode("utf-8")
    payload = {
        "init_images": [encoded],
        "prompt": prompt,
        "negative_prompt": negative_prompt,
        "denoising_strength": denoising_strength,
        "steps": 25,
        "cfg_scale": 7,
        "width": min(image.width, 1024),
        "height": min(image.height, 1024),
        "batch_size": 1,
        "n_iter": 1,
    }

    try:
        response = requests.post(
            f"{A1111_URL}/sdapi/v1/img2img",
            json=payload,
            timeout=300,
        )
        response.raise_for_status()
        data = response.json()
        output = base64.b64decode(data["images"][0])
    except requests.Timeout:
        raise HTTPException(504, "A1111 generation timed out")
    except (requests.RequestException, KeyError, IndexError, ValueError):
        raise HTTPException(502, "A1111 generation failed")

    return Response(content=output, media_type="image/png")

This wrapper is a reference, not a production-ready service. Add authentication, prompt and file-size limits, request IDs, structured logging, a queue, concurrency control, cancellation, storage policies, and stronger exception handling before exposing it to users.

Production security and operations

• Keep AUTOMATIC1111 on localhost or a private network.
• Expose only the authenticated wrapper.
• Validate file type from actual image content, not only the filename or MIME header.
• Limit file size, dimensions, prompt length, steps, batch size, and output count.
• Prevent arbitrary URL fetching and restrict filesystem access.
• Keep credentials and API keys out of client-side code.
• Use one queue per GPU and explicit maximum concurrency.
• Return backpressure when the queue is full rather than allowing unlimited work.
• Set generation timeouts and expose health and readiness states.
• Log request IDs and operational errors without unnecessarily storing private sketches or prompts.
• Warm workers so the first request is not confused with normal latency.
• Store outputs with a lifecycle policy and delete temporary files.

A1111 is not automatically a horizontally scalable job service. Concurrent requests can compete for GPU memory and make latency unpredictable. Model switching can also be expensive. The API distinguishes persistent options changes through /sdapi/v1/options from request-level overrides such as override_settings; a public wrapper should not allow arbitrary callers to change global server settings.

Debugging guide

Self-hosting versus a managed API

The Stability AI API reference documents a hosted sketch-control capability. It may be preferable when the requirement is simply a managed sketch endpoint. It is less suitable when users need arbitrary community checkpoints, custom LoRAs, local processing, or A1111-specific extensions.

RunPod can be a practical middle ground for a rented GPU, while Vast.ai may appeal to cost-sensitive technical users comfortable evaluating marketplace offers. Neither option removes the need to secure and operate the inference application.

Licensing, privacy, and model compatibility

“Open source” does not automatically mean unrestricted commercial use. Review the license for the checkpoint, VAE, LoRA, ControlNet model, and any other downloaded component. Also consider user-uploaded content rights, training-data restrictions, applicable laws, and platform policies.

A self-hosted deployment can keep sketches and prompts inside your infrastructure, but privacy also depends on cloud-GPU operators, logs, backups, object storage, and monitoring. Document what is retained and for how long.

Do not assume every ControlNet model works with every Stable Diffusion checkpoint. Verify the base architecture, model family, precision, expected resolution, required preprocessor, license, and VRAM requirements.

Quick Recap

Bestseller No. 1

Wacom Intuos Small, Wired Graphic Drawing Tablet with Pen + Software

$39.95

SaleBestseller No. 2

XPPen Deco 01 V3 10x6 Drawing Tablet, 16K Battery-Free Stylus, 8 Keys

$45.00

SaleBestseller No. 3

HUION Inspiroy H640P 6x4 inch Drawing Tablet 8192 Pen Pressure

$29.99

Bestseller No. 4

4 Pack LCD Writing Tablet for Kids, 8.5 Inch Colorful Doodle Board Drawing Tablet, Educational Learning Toys Birthday Gifts for Boys Girls Age 3 4 5 6 7 8

$9.99

SaleBestseller No. 5

XPPen Artist 13.3 Pro V2 Drawing Tablet with Screen, 16K, Full-Laminated

$211.00

Recommended implementation path

1. Run AUTOMATIC1111 locally with --api.
2. Verify the live schema at /docs and test the sampler endpoint.
3. Implement native img2img with one sketch, one prompt, one output, and a fixed resolution.
4. Tune denoising strength while keeping the seed and other settings recorded.
5. Install a compatible ControlNet extension and model if structural fidelity is insufficient.
6. Configure ControlNet successfully in the UI before reproducing the request programmatically.
7. Move the A1111 service behind a private network and authenticated backend.
8. Add validation, queueing, timeouts, concurrency limits, monitoring, and storage controls.
9. Review model and user-content licensing before commercial use.

ThatPainter Team

Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.