Vibe Coding DiscoverStoryMaker
View on GitHubStoryMaker: Towards consistent characters in text-to-image generation
StoryMaker is a diffusion personalization method and inference/training pipeline that keeps characters consistent across text-to-image generations, preserving faces, clothing, hairstyles and bodies. Built on SDXL with IP-Adapter, LoRA and InsightFace encoders.
Use Cases
Generate multiple images with consistent charactersKeep face, clothing, hairstyle and body identity across scenesBuild image-based stories and storyboardsPersonalized portrait / selfie generationMulti-character scene synthesis from reference photosTrain custom StoryMaker adapters on your own data
Built With
- Language
- Python
- Frameworks
- PyTorch · diffusers · transformers · InsightFace · OpenCV · IP-Adapter · SDXL · LoRA · Accelerate
Tags
text-to-image · character-consistency · personalization · diffusion · SDXL · IP-Adapter · LoRA · image-generation · face-preservation · story-visualization · training-code · inference-pipeline · diffusers · python