Kontext Presets via BFL API
Pick a preset task, add a few keywords, and send one or two images to Flux Kontext through the Black Forest Labs API. An LLM turns your keywords into the edit prompt.
- No GPU (runs on CPU)
- Image editing
- Free template
How it works
This graph has no local diffusion model. Images are loaded, resized with ImageResizeKJv2 and ResolutionSelector, and optionally stitched together with ImageStitch. BiRefNetRMBG is available for background removal, and FluxKontextImageScale prepares sizes.
Prompt writing is done by the llm-toolkit. A SystemPromptTaskGenerator holds a preset for each task, and PromptManager with LLMToolkitTextGeneratorStream expands your comma-separated keywords into a full instruction. A LocalTransformersProviderNode is included as a provider option. The finished prompt goes to ConfigGenerateImageBFL and GenerateImage through BFLProviderNode, which calls Flux Kontext on the Black Forest Labs API, and SaveImage stores the output.
The notes explain how to fill the keyword field. Some tasks, such as Remove Text and Remove Furniture, need nothing special, but the field cannot be empty, so enter a neutral word like subject. Four-variation tasks accept one to four comma-separated descriptors, for example dog, cat, bird for Add Pet.
Tips
- Match the input and output aspect ratio settings when you can.
- Use short descriptors, for example golden hour or neon noir, rather than full sentences.
- The Black Forest Labs step needs an API key.
- Use the four-variation tasks to explore options in one run.
What you can use it for
- Relighting a portrait with golden hour or neon looks
- Teleporting a subject into a new location
- Cartoon, anime or movie poster versions of a photo
- Interior design and furniture removal on room photos
Run it in three steps
Open the template
Click Run on ComfyDeploy. The workflow, its custom nodes and models are set up for you on a cloud machine.
Add your inputs
Provide input image and optional second image in the playground or the ComfyUI editor.
Run, share or deploy
Run it on a cloud machine, share it with your team as a playground, or deploy it as an API endpoint.
Frequently asked questions
What GPU does the Kontext presets workflow need?
It is listed as CPU, so it runs without a GPU. The editing is done by Flux Kontext on the Black Forest Labs API, using the BFLProviderNode.
Which presets are included?
The input notes list tasks such as Teleport, Move Camera, Relight, Product, Zoom, Colorize, Movie Poster, Cartoonify, Remove Text, Haircut, Bodybuilder, Remove Furniture, Interior Design, Season Shift, Age Progression, Add Pet, Historical Era, Dramatic Weather, Mirror World, Virtual Makeup, Pattern Overlay, Change Outfit and Double Exposure.
How do I run the Kontext presets workflow as an API?
Deploy the workflow on ComfyDeploy and call the generated endpoint. The ComfyUIDeployExternal input and output nodes in the graph become the request and response fields.
