Vibe Coder · Unit 20: Image Models: Flux, ComfyUI and LoRAs · Project
Milestone 20 of 23 · Optional for your role
A brand image kit
On-brand images from one saved workflow, with your own LoRA.
One product, built one milestone at a time
Vibe Coder has one project. You pick an idea in Unit 1 and every unit adds a piece to it, until the last unit launches it. Every milestone ends with a push to your own GitHub repository. Your product needs pictures that look like they belong together. This milestone builds a repeatable way to make them: a chosen model with a licence you have read, a saved ComfyUI workflow, and a LoRA trained on your own images. It is required for designers and marketers and optional for everyone else.
- 1Your builder’s kitA one-line product idea, your role, and five working accounts.
- 2A fact-checked product briefOne page on your idea, tested against how the models really behave.
- 3Your product project in ClaudeA project with instructions and files, and your first real piece of work from it.
- 4A brand kit and research fileA name, images and market research for your product, with a second opinion.
- 5Your prompt libraryThe prompts you will reuse to build the product, each one tested.
- 6Your product specThe problem, the people, the first version and how you will measure it.
- 7A clickable prototypeA version people can click through, shown to three of them.
- 8A working first draftYour product generated from the brief, with sign-in and data, in your own GitHub repository.
- 9The first working versionYour app running on your computer, built with Claude Code.
- 10Your Claude Code setupProject instructions, a custom command and a skill made for your app.
- 11One AI featureA feature in your app that calls a model, with its key kept safe.
- 12A connected assistantClaude or ChatGPT connected to a tool you already use, with the right permissions.
- 13Sign-in and saved dataAccounts and a database behind your app.
- 14Your app, liveOnline at its own address, updating every time you save.
- 15Your product’s back officeThe automatic jobs behind your product, as tested workflows in GitHub.
- 16An agent that works for your productOne agent with narrow tools, limits, approval and a test set.
- 17A helper that answers from your documentsAnswers with sources, scored on your own questions.
- 18A product that can chargeEmail from your own domain and a tested checkout, in test mode.
- 19A model tuned for one jobA small experiment, measured against your best prompt.
- 20A brand image kitOn-brand images from one saved workflow, with your own LoRA.
- 21A launch videoThirty to sixty seconds, with voice, music and sound.
- 22A tested, locked-down appEvery flow checked, and each person able to see only their own data.
- 23Your launched productThe finished product, in front of people, with a page that shows your work.
You start with
A model tuned for one job
A small experiment, measured against your best prompt.
Milestone 19Your product gains
A brand image kit you can reproduce
That makes 20 of 23 pieces in place.
Your role
The steps change with your role. Choose yours to see your version of this milestone.
Start with this prompt
Paste it into Claude or ChatGPT, or into Claude Code once you are building. Fill in the parts in square brackets with your own product.
I am making a set of images for my product. Here is the product and its visual style: [paste your design system or describe it] Help me write an image brief: the six to ten images the product needs, and for each one the subject, the setting, the light and the style in one sentence. Mark the ones that must contain readable text. Work with me one step at a time. Ask me one question, wait for my answer, then go on. Do not write the finished thing for me: show me a draft, tell me what is weak about it, and let me decide. Then help me decide which one subject or style is worth training a LoRA for, and what photos or artwork of my own I would need.
Build it step by step
7 steps, one from each lesson of the unit. Do each step after its lesson. A box you tick here is ticked in the lesson too.
Step 1 of 7 · from the lesson How image models work
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepA brand image kit Write your image brief
List the six to ten images your product needs: a hero image, feature pictures, social cards, an avatar or mascot. For each, write the subject, the setting, the light and the style in one sentence. Decide one visual style for all of them.
Done when
You will make these images in the next lessons, so keep the list where you can copy from it.
Step 2 of 7 · from the lesson Choosing a Flux model
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepA brand image kit Choose your model
For your image brief, decide where the images will be made (an API or your own machine) and which Flux model fits. Read its licence and write one line on why your use is allowed.
Done when
Keep this line with your image brief. It goes into your repository at the end of the unit.
Step 3 of 7 · from the lesson Your first ComfyUI workflow
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepA brand image kit Make your first image in ComfyUI
Open ComfyUI (Comfy Cloud is fine). Build or load the basic text-to-image workflow, write a prompt for one image from your brief, and run it. Then change only the seed and run it again.
Done when
This first model is small and the picture will be rough. The next lesson swaps in Flux.
Step 4 of 7 · from the lesson Flux in ComfyUI
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepA brand image kit Make three images with Flux
Load a FLUX.2 template, put the model files in place (or use Comfy Cloud), and make three images from your brief. Use one reference image so the product or character matches across them. Save the workflow with a clear name.
Done when
Keep the saved workflow file. It is part of what you publish at the end of the unit.
Step 5 of 7 · from the lesson Editing and control
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepA brand image kit Finish your images by editing
Take the three images from the last lesson and bring each to a finished state. Use one instruction edit, one inpaint and one outpaint across the set. Keep every version.
Done when
Keep the before and after of one edit. It makes a good line in your project write-up.
Step 6 of 7 · from the lesson Training a LoRA
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepA brand image kit Train a LoRA for your product
Choose one subject or style from your image brief. Collect a clean, varied set of images you own, caption each with a trigger word, and train a LoRA on FLUX.2 klein 4B Base with AI-Toolkit or a hosted trainer. Keep the samples.
Done when
Keep the dataset folder and the caption files. They are worth more than the LoRA file, because you can retrain from them.
Step 7 of 7 · from the lesson Using your LoRA
Read the short notes and pictures.Do everything inside a blue frame.
ActivityBuild stepA brand image kit Publish your brand image kit
Load your LoRA, run a test grid, choose a strength, and produce the final images from your brief. Then put the kit in your product’s GitHub repository: the final images, the saved workflow, the prompt template, the caption files, and a short README.
Done when
Leave the LoRA file itself out of the repository if it is large. Say in the README where it is kept.
Publish it to GitHub
Your product repository
Add the brand-kit/ folder: the final images, the workflow file, the prompt template, the captions and a README naming the model and its licence. Commit and push.
A milestone is not finished until it is pushed. A public repository with a history is how other people, including employers, can see what you built. Never commit a key, a token or anyone’s private data.
When it is done
Every box above is ticked, the work is pushed to GitHub, and you can show the result to someone who has not seen it before. Then move on: milestone 21 is a launch video.