π Nick & Charlie | LoRA β Heartstopper | Base: ANIMA
Captures the iconic hand-drawn art style of Alice Oseman's Heartstopper webcomic and brings Nick Nelson and Charlie Spring to life in ANIMA.
π Before anything else
This LoRA took a lot of work β picking the images, building the dataset and tags, training, and testing the checkpoints. If you have a moment, drop a Like and especially post your results in the comments (with the prompt/settings you used) β it helps me a lot to know what to improve in the next versions. π₯
β οΈ The model was trained without any NSFW images and without any photos of the live-action actors. It is strictly based on the original graphic novel / webcomic art style. Use it respectfully.
π¬ Check out the image descriptions and prompt examples on the posted preview images β they show how the prompts are structured!
π¬ Leave your generations in the comments, and tag the LoRA so I can see how it's looking β it would help a lot.
π¦ Trained with 92 carefully selected images in total from the original webcomic art.
π About this model
The main goal of this LoRA is to capture the iconic hand-drawn art style of Alice Oseman's Heartstopper webcomic and bring Nick Nelson and Charlie Spring to life in ANIMA.
While the LoRA is not 100% perfect, it works extremely well!
π¬ Just to remind you, the comics have simple backgrounds and pastel tones, emphasize this in the prompt, otherwise the characters won't 'match' the rest of the work
π Nick Nelson
Nick generates consistently with high quality across most poses and outfits. His facial features, hair shape, and athletic frame lock in very reliably.
π Charlie Spring
Charlie's output quality depends significantly on the generation resolution. Since the original comic source drawings vary widely in scale and detail, generating Charlie effectively may require a few resolution tweaks and test runs until you find the sweet spot for your specific scene.
π¨ Using the Art Style with Other Characters
If you want to extract the Heartstopper art style without generating Nick or Charlie:
Use the trigger tags
heartstopper+webcomicin your prompt.Combine this with other character LoRAs to apply Heartstopper's unique hand-drawn pastel aesthetic to any character!
βΉοΈ Generation tips
Resolution Flexibility: There is no single "standard resolution" for this LoRA. Because the source art varies greatly, trying different resolutions (portrait, square, or wide 2:3 / 3:4) depending on scene context makes a huge difference in image quality.
Fixed Seed Testing: When experimenting with resolutions or prompt tweaks, try using a fixed seed to observe how resolution directly impacts detail and character rendering.
Recommended starting point: On ANIMA base with 12 steps + acceleration LoRA, the output keeps a clean hand-drawn webcomic feel that fits Heartstopper perfectly.
Check the descriptions of the posted preview images β they demonstrate how to structure tags and natural language descriptions (or multi-panel layouts) for best results.
βοΈ Generation settings used for preview images
All preview images were generated using:
Base model: Anima 1.0
Acceleration LoRA: strength 1.0
CLIP: anima default
Steps: 12
CFG: 1.0
Sampler:
er_sde - betaImage size: thereβs no fixed resolution for this LoRA; it works at resolutions above 512x and in any format, although the performance is pretty hit or miss. I recommend testing various resolutions for your specific prompt.
π One more thing
I'm just getting started with this β if you have a moment, drop a Like and share your generations with the settings you used. It really helps me improve the next versions. Have fun! π



