Image Generation

​

Instruct AI to describe the image

With Auto AI, you can create a block and simply instruct it to generate the image you need. We’re going to do it a bit more manually this time, so that we can introduce some additional UI elements.

We’ll create two blocks, one to figure out a good image to go along with the blog post and a second to generate the image.

Click the (+) handle to the right of the final blog post block to create a new AI block. This will be our ‘image description’ block.

We’ll instruct the image description block as follows:

Describe a good image for this blog post. Nothing too sci fi. Provide details about the style and composition. Keep it simple. Around 100 words. Maybe a laptop with some code.

Here’s what your canvas should look like after adding the image description block:

​

Generate the hero image

Add a block to the right of the image description. To manually select a model, click ‘All’ at the top left of the block, then search for SD3 and select Stable Diffusion 3 Large (our preferred image generation model right now).

Here’s what the model search looks like:

Click Run to execute the image generation task. The AI model will process the instructions and generate the hero image for your blog post.

Your canvas should now have an appealing hero image to accompany the blog post:

​

Play!

Hunch makes it quick, easy and fun to experiment with AI models and generate creative outputs. Try changing the image description prompt or selecting a different image generation AI model. See if you can figure out how to get the AI to combine the final blog post and image into a single cohesive output!