Finetune Images on Story
Learn how to use the FLUX Finetuning API to finetune images and then register the output on Story in TypeScript.
In this tutorial, you will use the FLUX Finetuning API to take a bunch of images of Story’s mascot “Ippy” and finetune an AI model to create similar images along with a prompt. Then you will monetize and protect the output IP on Story.
This Tutorial is in TypeScript
Steps 1-3 of this tutorial are based on the FLUX Finetuning Beta Guide, which contains examples for calling their API in Python, however I have rewritten them in TypeScript.
The Explanation
Generative text-to-image models often do not fully capture a creator’s unique vision, and have insufficient knowledge about specific objects, brands or visual styles. With the FLUX Pro Finetuning API, creators can use existing images to finetune an AI to create similar images, along with a prompt.
When an image is created, we will register it as IP on Story in order to grow, monetize, and protect the IP.
0. Before you Start
There are a few steps you have to complete before you can start the tutorial.
- You will need to install Node.js and npm. If you’ve coded before, you likely have these.
- Add your Story Network Testnet wallet’s private key to
.env
file:
- Go to Pinata and create a new API key. Add the JWT to your
.env
file:
- Go to BFL and create a new API key. Add the new key to your
.env
file:
- Add your preferred Story RPC URL to your
.env
file. You can just use the public default one we provide:
- Install the dependencies:
1. Compile the Training Data
In order to create a finetune, we’ll need the input training data!
- Create a folder in your project called
images
. In that folder, add a bunch of images that you want your finetune to train on. Supported formats: JPG, JPEG, PNG, and WebP. Also recommended to use more than 5 images. - Add Text Descriptions (Optional): In the same folder, create text files with descriptions for your images. Text files should share the same name as their corresponding images. Example: if your image is “sample.jpg”, create “sample.txt”
- Compress your folder into a ZIP file. It should be named
images.zip
2. Create a Finetune
In order to generate an image using a similar style as input images, we need to create a finetune. Think of a finetune as an AI that knows all of your input images and can then start producing new ones.
Let’s make a function that calls FLUX’s /v1/finetune
API route. Create a flux
folder, and inside that folder add a file named requestFinetuning.ts
and add the following code:
Official Docs
In order to learn what each of the parameters in the payload are, see the official /v1/finetune
API docs here.
Next, create a file named train.ts
and call the requestFinetuning
function we just made:
Warning: This is expensive!
Creating a new finetune is expensive, ranging from 6 at the time of me writing this tutorial. Please review the “FLUX PRO FINETUNE: TRAINING” section on the pricing page.
This will log something that looks like:
This is your finetune_id
, and will be used to create images in the following steps.
3. Wait for Finetune
Before we can generate images with our finetuned model, we have to wait for FLUX to finish training!
In our flux
folder, create a file named finetune-progress.ts
and add the following code:
Official Docs
In order to learn what each of the parameters in the payload are, see the official /v1/get_result
API docs here.
Next, create a file named finetune-progress.ts
and call the finetuneProgress
function we just made:
This will log something that looks like:
As you can see, the status is still pending. We must wait until the training is ‘Ready’ before we can move on to the next step.
4. Run Inference
Warning: This costs money.
Although very cheap, running an inference does cost money, ranging from $0.06-0.07 at the time of me writing this tutorial. Please review the “FLUX PRO FINETUNE: INFERENCE” section on the pricing page.
Now that we have trained a finetune, we will use the model to create images. “Running an inference” simply means using our new model (identified by its finetune_id
), which is trained on our images, to create new images.
There are several different inference endpoints we can use, each with their own pricing (found at the bottom of the page). For this tutorial, I’ll be using the /v1/flux-pro-1.1-ultra-finetuned
endpoint, which is documented here.
In our flux
folder, create a finetuneInference.ts
file and add the following code:
Official Docs
In order to learn what each of the parameters in the payload are, see the official /v1/flux-pro-1.1-ultra-finetuned
API docs here.
Next, create a file named inference.ts
and call the finetuneInference
function we just made. The first parameter should be the finetune_id
we got from running the script above, and the second parameter is a prompt to generate a new image.
This will log something that looks like:
As you can see, the status is still pending. We must wait until the generation is ready to view our image. To do this, we will need a function to fetch our new inference to see if its ready and view the details about it.
In our flux
folder, create a file named getInference.ts
and add the following code:
Official Docs
In order to learn what each of the parameters in the payload are, see the official /v1/get_result
API docs here.
Back in our inference.ts
file, lets add a loop that continuously fetches the inference until it’s ready. When it’s ready, we will view the new image.
Once the loop completed, the final log will look like:
You can paste the sample
into your browser and see the final result! Make sure to save this image as it will disappear eventually.
5. Set up your Story Config
Next we will register this image on Story as an IP Asset in order to monetize and license the IP. Create a story
folder and add a utils.ts
file. In there, add the following code to set up your Story Config:
Associated docs: TypeScript SDK Setup
6. Upload Inference to IPFS
Now that we have made a new inference, we’ll have to store the image sample
file ourselves on IPFS because the sample is only temporary.
In a new pinata
folder, create a uploadToIpfs.ts
file and create a function to upload our image and get details about it:
We will now use this function in the following step.
7. Set up your IP Metadata
In your story
folder, create a registerIp.ts
file.
View the IPA Metadata Standard and construct the metadata for your IP as shown below:
8. Set up your NFT Metadata
In the registerIp.ts
file, configure your NFT Metadata, which follows the OpenSea ERC-721 Standard.
9. Upload your IP and NFT Metadata to IPFS
In the pinata
folder, create a function to upload your IP & NFT Metadata objects to IPFS:
You can then use that function to upload your metadata, as shown below:
10. Register the NFT as an IP Asset
Next we will mint an NFT, register it as an IP Asset, set License Terms on the IP, and then set both NFT & IP metadata.
Luckily, we can use the mintAndRegisterIp
function to mint an NFT and register it as an IP Asset in the same transaction.
This function needs an SPG NFT Contract to mint from. For simplicity, you can use a public collection we have created for you on Aeneid testnet: 0xc32A8a0FF3beDDDa58393d022aF433e78739FAbc
.
Associated Docs: ipAsset.mintAndRegisterIp
11. Register our Inference
Now that we have completed our registerIp
function, let’s add it to our inference.ts
file: