Imagev1.0.0

Flux Kontext

Edit an image with text instructions while preserving character identity and style consistency.

6 inputsIMAGE

Run it now Call from code

Prompt: “turn it into a soft watercolor painting”

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 flux-kontext-dev 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("flux-kontext-dev", {
  prompt: { value: "example" },
  image: { ref: "https://..." },
  aspectRatio: { value: "match_input_image" },
  outputFormat: { value: "webp" },
  steps: { value: 28 },
  seed: { value: 1 },
});

# Install once, then sign in
npm install -g blitflow
blitflow login

blitflow node flux-kontext-dev \
  -i prompt="example" \
  -i image=@https://... \
  -i aspectRatio="match_input_image" \
  -i outputFormat="webp" \
  -i steps=28 \
  -i seed=1

{
  "name": "runs_node",
  "arguments": {
    "node": "flux-kontext-dev",
    "inputs": {
      "prompt": {
        "value": "example"
      },
      "image": {
        "ref": "https://..."
      },
      "aspectRatio": {
        "value": "match_input_image"
      },
      "outputFormat": {
        "value": "webp"
      },
      "steps": {
        "value": 28
      },
      "seed": {
        "value": 1
      }
    }
  }
}

curl https://studio.blitflow.com/api/v1/runs/node \
  -H "Authorization: Bearer $BLITFLOW_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"node":"flux-kontext-dev","inputs":{"prompt":{"value":"example"},"image":{"ref":"https://..."},"aspectRatio":{"value":"match_input_image"},"outputFormat":{"value":"webp"},"steps":{"value":28},"seed":{"value":1}}}'

Schema

Inputs

prompt*	TEXT
image	IMAGE	Image to edit
aspectRatio	TEXT	match_input_image · 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3	match_input_image
outputFormat	TEXT	Format webp · jpg · png	webp
steps	INT		28
seed	INT

Outputs

image