Krea 2 (and probably other image models): Infinite Character Consistency Using Descriptions + ComfyUI

Ok, so long story short, I saw a few workflows that enabled Krea 2 inside ComfyUI to generate a single image with four panels in order to keep character consistency. Nice idea, but for me there was one problem: resolution. Four panels inside one image is a no-go for the kind of work I do.

Then I had a different idea.

What if Krea is simply good enough that, with sufficiently detailed descriptions, it doesn’t need previous images at all? What if every scene completely recreates the characters from scratch?

So I tested it.

It works surprisingly well.

The characters remain remarkably consistent across an essentially unlimited number of separately generated images.

The workflow is at the end of the article.

The idea came to me after sorting trough a lot of Ace Step 1.5 XL outputs and trying to find best styles and tags for songs. Why not automate the generation process AND the review process, or at least make it easier. So as usual I used Qwen LM and Qwen VL (compared to something like olama these ones run directly in comfy and do not require a server) to randomize the tags on each run, but more importantly to try and rate the output. How ? By converting the audio output into a set of waveforms for 4 segments of the song that I feed into Qwen VL as an image and ask it to subjectively look at the waveform and give it feedback and rating, rating that is used then to also name the output file. Like this. I am not sure it works properly but the A+ rated songs were indeed better than B rated ones.
Workflow is here. Install the missing extensions and add the qwen models.