Distillery AI Image Generator Got A Major Update

It’s only been a few weeks since I published a review article about Distillery. I was impressed by this new AI image generator tool because it combines Stable Diffusion’s level of control and Midjourney’s quality.

Today, they have released some exciting new features which are worth checking out.

What is Distillery?

Distillery is the brainchild of FollowFox.ai, a small team dedicated to developing fully open-source AI solutions. It is an advanced AI text-to-image generator that offers incredible control over the image creation process.

Th extensive parameter control allows users to adjust the parameters for precise image customization. This level of control is nearly unmatched, making Distillery perfect for advanced and power users.

Later in this post, I will give real-life use-case examples and demonstrate how different parameters contribute to the process. It may take some time to fully learn using this AI tool, but after achieving a certain level, this tool stands is just as good, sometimes even better than the competitors.

Here are the features offered by Distillery today:

• Negative Prompt
• Seed
• CFG
• Aspect Ratio
• Denoise Strength
• Model
• LoRAs
• Controlnet
• Image to Image
• Inpainting
• LLM Prompt Assistant
• IP Adapter
• Sharpen
• Sampler
• Raw Mode
• Upscale Method

Creating promotional material for your business

In this example, I will create a quick promotional material for your business. This example will showcase how drastically your time spent will be reduced in creating such materials.

The goal is to create a promo image for an eyewear shop called “Sola” for Halloween.

Prompt: Grim Reaper standing outside his newly opened eyewear shop ‘SOLA’

The output image may need some tweaks for finer details, but the overall quality is great and is ready to be used for social media. I love how AI added its own interpretation to the image: putting eyewear on the character or adding a banner to the window of the shop.

Some generations can come out as messy, but even they can lead to surprisingly good ideas you can leverage for your campaign. Those mutations introduce an element of unpredictability and randomness into the creative process. It can provide artists with unexpected and novel combinations, sparking new ideas and pushing the boundaries of traditional artistic approaches.

In order to generate the above image, we have used a few different parameters. Below is a list of them and their respective explanations:

1. Model Mohawk — SDXL-based model inside Distillery, which is great for creating characters
2. LoRA Texta — There are 100+ LoRAs available on Distillery. Each of them enhances a specific style. You can mix up to five different LoRAs. For this image, we used ''texta'', which improves text creation on images
3. Adapt—After the first couple of generations, we chose the best one and used the adapt function to re-generate new ones. That is how we got to the image above. Here is the explanation of this function from the documentation of Distillery: “…allows the model to ‘perceive’ the input image as a prompt. As the authors of the paper mention, “an image is worth a thousand words,” and indeed, it is a powerful tool that comes with a bit of a learning curve but gives a whole lot of new capabilities to the model.’’
4. Control — We used the control function for the same purpose as the adapt function. The feature allows users to provide a reference image as an input that will guide the image generation process.

Using Inpainting Function to Enhance the Image

After the initial generation, we started enhancing the image further. There are a bunch of things that can be done in Distillery, but for now, we mainly focus on inpainting.

Inpaint is a powerful tool that lets you do a new generation only on a specific part of the image. When compared to other tools, Distillery’s inpainting stands out with its quality, ability to follow the outline, and ability to make the new generation look natural.

We combined adapting and inpainting functions to enhance the image with a fire next to the brand name.

The image below explains how the whole process works. First, you create a mask, which is an empty white box. You create a new prompt that inpaints only in that box. To enhance our “fire”, we provided the given fire image as an input element.

Distillery parameters used: 1. Makemask — Used to cover a part of the image

1. Inpainting — parameter that generates new prompt only in covered part
2. Adapt — Same as we explained above
3. Negative input—by adding negatives to the prompt, certain elements or characteristics are excluded from your generated image.

We can use the same technique to change the face of our character.

Combining the Uncombinable

When trying to push the limits of Distillery, I tried to combine a painting with our initial image generation with the hope of getting a background that resembles the painting.

Surprisingly, it did super well. Also, the results are from the first try. I have not tweaked any additional parameters to try and see what will come up.

Final thoughts

Overall, Distillery has proven to be a very powerful tool. They are still Discord-based, which makes it less comfortable for some users compared to web-based solutions, but their parameter control is pretty much unmatched.

What I enjoy on top of the technology offering is the community of Distillery, which is very helpful and supports your journey on the platform, which makes it easier to get used to it.

They pulled off a great update compared to the previous time I reviewed them, and as per their announcement, it is just the beginning.

Check out their website, Followfox.ai, to learn more about the company and their products.

Discord link — https://discord.com/invite/FSecryv3S8