Solutions to “Just KNIME It!” Challenge 5 - Season 4

:nerd_face: Hi, folks, a new Just KNIME It! challenge is out!

:house: This week, let’s help Interior Designer Emma refresh a part of a house on a budget. :money_with_wings: Can you combine prompting and GenAI image generation to loop through various styles and produce visual proposals that Emma’s client will love? :heart_eyes:

Here is the challenge. Let’s use this thread to post our solutions to it, which should be uploaded to your public KNIME Hub spaces with tag JKISeason4-5 .

:sos: Need help with tags? To add tag JKISeason4-5 to your workflow, go to the description panel in KNIME Analytics Platform, click the pencil to edit it, and you will see the option for adding tags right there. :blush: Let us know if you have any problems!

4 Likes

Hi All,

Finally cracked the advance level. After updating my Knime version and verifying my identity on OpenAI :sweat_smile:. Here is my updated solutions.

Workflow:

Output:

Cheers and Happy Analyzing :slight_smile:

10 Likes

Is there a free method for using Gen AI in Knime?

2 Likes

Hello Everyone, Happy Wednesday.

Here is my solution for this Challenge - JKISeason4-5_Sampath – KNIME Community Hub

Workflow-

Result-

Thank you
Sampath

9 Likes

6 Likes

It has been a blast to have such a variety of challenges and nodes to “study” each week.

This is my solution:JKISeason4-5 – KNIME Community Hub

7 Likes

Hi all! Happy Wednesday!

What an interesting one! Always good to bring the head back at GenAI and use the native nodes from KNIME (not Python :wink: ).

Here is my workflow: JKISeason 4-5 - Interior Design with GenAI – KNIME Community Hub

And it includes all the objectives proposed in the challenge description :sunglasses:.
A bit of flexibility implemented - the list of style is defined in a table and the room to focus on is defined in the String Widget.

Here is the output within the Data App.

A snapshot of the workflow below.

Enjoy the challenge all!!

Cheers
Jerome

10 Likes

Guess i had to update my Knime to see this updated Node OpenAI Image generator node :sweat_smile:

1 Like

Here’s my solution. Could not get a verification for OpenAI so I used Dall. This prevented editing the base image, but does produce credibly themed images.


8 Likes

What version are you using ?
With KNIME 5.4.3, you have to install the KNIME AI Extension (which seems to be in the Labs extension).

1 Like

I was using Knime v5.2 :sweat_smile:
Latest seems to be 5.4.

I have the extension and previous name of the node seems to DAl-E view.

2 Likes

Hi KNIME’ers! :wave:

I’ve just uploaded my solution for Week 5 of Just KNIME It!

In this version, I added a little extra — now Emma, our interior designer, can upload her interior photos directly :camera_flash: and automatically get the results sent to her via email! :love_letter:

Super fun to build, and once again amazed by how flexible KNIME is, no heavy coding needed!

Check it out here:

:link: JKISeason4-5 arief_rama – KNIME Community Hub

10 Likes

Very nice solutions, folks! :heart_eyes: :clap:

I bet Emma and her client will be happy with the design proposals :grin:.

Keep it up!

7 Likes

Hey @roberto_cadili ! :smile:

This challenge really made my API usage at https://platform.openai.com go up like crazy :rocket::money_with_wings:
But that’s okay — if it helps Emma get the solution she needs, it’s totally worth it! :joy:

Fingers crossed she enjoys using it… and that my API quota survives this season! :sweat_smile:

4 Likes

Wondering the same. In other workflows I have already experimented with HuggingFace models. However, I do not seem to be able to get it work with generating images… Curious whether a solution exists

2 Likes

I am keeping my fingers crossed for the same :crossed_fingers:t3::sweat_smile::joy:

1 Like

Unfortunately, I am not aware of good free and open-source models for image generation and editing.

Some of the vision models that you find on Hugging Face, for example those provided by Stable Diffusion (https://huggingface.co/stabilityai/stable-diffusion-3.5-large), are good but still require some form of pay subscription if you want to use them for out-of-the-box API inference, or some quite technical fiddling if you want to use the files locally.

On Ollama, you can find some decent vision models, for example LLama 3.2-vision (https://ollama.com/library/llama3.2-vision), but this model is designed for visual recognition, image reasoning, captioning, and answering general questions about an image (see an example workflow with Llava model). So, not really image generation and editing.

But please let me know if you find a good free model for image generation and editing. Even better if it’s available via a an easy to use and free API :slight_smile:.

4 Likes

I think there is:

For “Classic Gen AI” (text generation), there is

  • Huggingface nodes (for free models)
  • GPT4ALL (for local models)

For image generation it’s trickier, I used python view node, where I called a huggingface model which generated the image for me. As it is more complicated I created an example workflow for that:

9 Likes

Hi Roberto! I just see your reply now (after replied to Soybeans0000023) :smiley:

I think on Huggingface you can find free models to generate images for you, but as KNIME doesn’t have built in image nodes for Huggingface AI you have to call it from python (with a python view node).

I have created a workflow how I created images with python view (uploaded to my public Hub):

For that example, I used the “black-forest-labs/FLUX.1-schnell” Huggingface model:

6 Likes

Find herewith my Submission on Challenge 5:JKISeason4-5 – KNIME Community Hub


6 Likes