renderartist/Toon-Tacular-Qwen-LoRA

Toon-Tacular Qwen

Prompt

Title with the upper space big yellow and pink bubble font overlapping playful letters "TOON-TACULAR QWEN" cartoon is stereotypical male bank robber who is holding a large bag of money with bills hanging out of the top of the bag. The burglar's widened eyes darting to toward the viewer with an expressive look of dismay and surprise, he's wearing a black and white striped long sleeve shirt, a yellow beanie, black plain boots and has a bushy brown mustache. Vibrant saturated colors with a bold cartoon animation style. classic cartoon style. 3/4 angle view. t00n style, zoomed out view, a high-energy 90s cartoon aesthetic. The background has painterly details, is detailed. The background is the interior of a metropolitan bank lobby.

Negative Prompt

shadows

Prompt

A nerdy man with curly red hair and square rimmed glasses, he wears a teal blue tropical shirt that has yellow flowers print, a white undershirt with a collar, front teeth are exagerrated and crooked, expressive motion pose with hands. Use vibrant cel-shaded colors and painterly background details to create a sense of dimension and depth. The background is the interior of a tropical cafe diner. t00n style, zoomed out view, a high-energy 90s cartoon aesthetic.

Prompt

t00n style, zoomed out view, a high-energy 90s cartoon aesthetic. An obese woman with pink hoop earrings updo messy hair, her front teeth are exagerrated and crooked and larger than the others, show teeth smile, jowels, smiling wacky expression. Use vibrant cel-shaded colors and painterly background details to create a sense of dimension and depth.

Prompt

t00n classic retro cartoon cowboy, the cowboy is riding a comical horse in a desert scene backdrop there are cactuses in the foreground creating a sense of depth

Prompt

t00n a cartoon wideshot scene of an old fat farmer witha beard and a hat petting a pig on a farm near a barn door, in the foreground are pitchforks and a bale of hay. the painterly background is sharp and focused with color gradients that enhance detail add a sense of depth and clarity.

Prompt

cartoon woman with blonde beauty with braided hair and white frilly hat pointing right while seated in dark paneled room with ornate gold chair arm visible, her facial expression shows narrowed eyes and pursed lips, soft directional lighting from left casting gentle shadows, muted color palette with saturated reds and blues rendered in clean 2D animation style - background is the interior of a royal manor.

Prompt

t00n a cartoon wideshot scene of an diva woman sitting in an orange upholstered chair outdoors in big sunglasses, she has red curly updo hair red lips happy facial expression, she has star shaped earrings, tilted head, she's smiling showing her teeth. the painterly background is sharp and focused with color gradients that enhance detail add a sense of depth and clarity.

Prompt

A storybook themed large king male stereotype in a 3/4 turn action pose. The setting is a retro-style castle exterior bridge, mature trees. The lighting is soft and even, casting gentle shadows. The color grading is warm with moderate saturation cartoon t00n

Prompt

A storybook themed fat mean queen female, large auburn curly big hair, stereotype villain red dress with linear high collar in a 3/4 turn action pose. The setting is a retro-style castle exterior bridge, mature trees. The lighting is soft and even, casting gentle shadows. The color grading is warm with moderate saturation cartoon t00n - the queen has an upturned nose and arrogant facial expression, strutting pose, one of her hands is visible with thick fingers cartoonish proportion.

Prompt

-

Prompt

-

Model description

Trained on 70 curated images, the Toon-Tacular Qwen LoRA breathes character and expression into your generated images. The style is reminiscent of mid-to-late 90s and early aughts cartoons. The dataset was regularized by using an edit model to upscale and unify the style to be consistent. The goal was to give all the aesthetic with less of the degradation/compression.

The LoRA was trained with the fp16 version of Qwen Image 2512, and tested with the same model, it's far from perfect but generally maintains the style consistently. This LoRA currently has weaknesses with overly busy backgrounds, smaller faces and some anatomy. The trigger word is t00n but it's not necessary to use it, simply including words like animation or cartoon triggers the style. Use an LLM and be strategic in your prompting for the best results, this isn't a one shot type of LoRA.

The first image in the gallery will contain a workflow that I used to generate the image. You don't have to use it but I'm including the embedded workflow in the image for completeness. You're welcome to modify to fit your use case. If it doesn't work for you then please skip it, I will not be offering support beyond sharing it.

Trained with ai-toolkit and tested in Comfy UI.

Trigger Word: t00n Recommended Strength: 0.7-0.9 Recommended Sampler/Scheduler: Euler/Beta

renderartist.com

Trigger words

You should use t00n to trigger the image generation.

Download model

Download them in the Files & versions tab.