All models
Imagev1.0.0

ControlNet Scribble

Generate a detailed image from a prompt while preserving a scribbled composition.

9 inputsIMAGEIMAGE
Demo coming soon
Demo coming soon

Run the node

IMAGE
Scribble
TEXT
TEXT
1 – ∞INT
0.1 – 30FLOAT
TEXT
TEXT
FLOAT
Noise
INT
Sign in to run

Running a model executes it on your account. Browsing the catalog stays free and needs no account.

Output

Fill in the inputs and run the node to see its output here.

Run it from your code

The same node, called by id from any surface. Every tab pins controlnet-scribble and passes the ports below. Full guide.

import { BlitClient } from "@blitflow/sdk";

const { runNode } = new BlitClient({ apiKey: process.env.BLITFLOW_TOKEN });

const { outputs } = await runNode("controlnet-scribble", {
  image: { ref: "https://..." },
  prompt: { value: "example" },
  imageResolution: { value: "512" },
  steps: { value: 20 },
  guidance: { value: 9 },
  additionalPrompt: { value: "best quality, extremely detailed" },
  negativePrompt: { value: "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality" },
  eta: { value: 0 },
  seed: { value: 1 },
});

Schema

Inputs

image*IMAGE
Scribble
prompt*TEXT
imageResolutionTEXT
256 · 512 · 768
512
stepsINT20
guidanceFLOAT9
additionalPromptTEXTbest quality, extremely detailed
negativePromptTEXTlongbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
etaFLOAT
Noise
0
seedINT

Outputs

imageIMAGE
Generated image
scribbleIMAGE
Processed scribble