| title: Instruction Image Editor · gr.Workflow | |
| emoji: 🖼️ | |
| colorFrom: indigo | |
| colorTo: purple | |
| sdk: gradio | |
| sdk_version: 6.22.0 | |
| app_file: app.py | |
| pinned: false | |
| hf_oauth: true | |
| hf_oauth_scopes: | |
| - inference-api | |
| # 🖼️ Instruction Image Editor | |
| Upload an image, type an edit instruction (for example *"turn it into a snowy winter scene"*, *"add sunglasses"*, *"make the car red"*), and get the edited photo back. | |
| The whole app is a single `gr.Workflow` `model` node calling [`black-forest-labs/FLUX.1-Kontext-dev`](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev) on Hugging Face Inference Providers. No client code, no API wiring: | |
| ``` | |
| [Image] ─┐ | |
| ├─▶ (model) FLUX.1-Kontext-dev ─▶ 🖼️ Edited image | |
| [Edit instruction] ─┘ | |
| ``` | |
| > This demo calls a Hugging Face model, so click **Sign in with Hugging Face** on the canvas before you run it. The edit then runs under your own token. | |
| From the blog *[Build Anything with gr.Workflow](https://huggingface.co/blog)*. | |