Version Detail
Trained by Tensor
Qwen-Image
3000
10
This is a fun and loose style I developed based on a mix of cartoon and marker renderings. Its meant to feel loose, exaggerated, and cartoonish. The style is prompted by using the trigger phrase "marker rendering style, " and then does best if you start your prompt with something like "a cartoon image of a (Your prompt here)" or "an animated image of a (Your prompt here)".
This model should default to a simple background if not prompted for more. The colors on this style lean towards a neutral grey that also has pops of colors to give accent and draw focus.
This model is trained with a focus on square images as I started with only 100 images for this training. I recommend treating it like you would any Qwen LoRA and testing it at the settings you would normally run. Most of my images are run at 2.5 cfg with with 20 steps on Euler Simple.
Project Permissions
Use in TENSOR Online
As a online training base model on TENSOR
Use without crediting me
Share merges of this model
Use different permissions on merges
Use Permissions
Sell generated contents
Use on generation services
Sell this model or merges







