Comics generator for PocketFM
A browser studio that turns a script or prompt into editable comic and webtoon panels. This is not “generate an image”: the product has a production structure — Show → Chapter → Workflow → frames, a custom
- 01 A script → editable comic panels, not a single image.
- 02 Heroes stay themselves: a model is trained per character.
- 03 A custom editor right in the browser.
A character has to stay itself in every frame.
A comic is not one image but dozens of frames where the same hero has to stay recognizable, in a layout the author can edit. Raw diffusion drifts: the same prompt yields a different face and outfit from one generation to the next. And the author needs a real editor, not a “generate again” button.
- A comic is dozens of frames, not a single image.
- The same character has to stay recognizable in every frame.
- Raw diffusion drifts — face and clothing change from generation to generation.
- The author needs an editor, not a “generate again” button.
A generation pipeline, a custom editor, and a model per character.
Generation lives inside a clear production structure, the author controls the composition of each frame, and a dedicated model is trained per hero so it stays itself. Everything runs on our own GPUs.
- 01
Structure the production
Show → Chapter → Workflow → frames: generation happens inside a clear structure rather than an empty prompt box.
- 02
Hold the character
A dedicated model (LoRA) is trained per hero — it stays recognizable frame to frame. This is the headline feature.
- 03
Control the composition
ControlNet (scribble/pose/canny/depth), img2img and face-aware inpainting — the author sets the frame instead of relying on luck.
- 04
Edit in the browser
A custom <canvas> editor: drawing, masks, image tooling. State is saved as a JSON snapshot per workflow.
- 05
Run on our own GPUs
Training and inference run on self-hosted GPU EC2, with shared model files on EFS.
A diffusion pipeline wrapped in a product.
Python/Django backend with a typed Django-Ninja API and Postgres; a React/Next.js frontend served as a static build on S3 + CloudFront. The AI pipeline is Stable Diffusion XL through ComfyUI workflows: ControlNet, img2img, face-aware inpainting, IP-Adapter and IP-Adapter-FaceID for face and clothing consistency, and upscaling.
A LoRA is trained per character (kohya). Training and inference run on self-hosted GPU EC2, with shared model files on EFS, accessed via IAM STS.
Stable Diffusion XL through ComfyUI workflows.
ControlNet (scribble/pose/canny/depth), img2img, face-aware inpainting.
IP-Adapter / IP-Adapter-FaceID — face and clothing consistency.
Per-character LoRA training (kohya).
A custom <canvas> editor, state saved as a JSON snapshot per workflow.
Self-hosted GPU EC2 + EFS, Django-Ninja API, Next.js on S3 / CloudFront.
What changed
The studio reached production
The V1 browser studio for AI comics and webtoons was built and shipped to production.
Characters hold frame to frame
Training a model per hero solved the core problem — recognizability across a series of frames.
Authors edit instead of re-rolling
A custom <canvas> editor gave control over the frame instead of betting on a lucky generation.
Need a generative product, not just a model call?
We build generative pipelines into products: composition control, character consistency, a custom editor, and inference on our own GPUs.