story-iter and 1Prompt1Story
These are competitors—both tackle multi-image narrative generation from text, with story-iter using iterative refinement across frames while 1Prompt1Story achieves consistency through a single-prompt mechanism, requiring users to choose between the training-free iterative approach versus the prompt-engineering approach.
About story-iter
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
Implements a plug-and-play Global Reference Cross-Attention (GRCA) module that iteratively refines generated frames by incorporating all previous reference images during diffusion denoising, enabling semantic consistency across long sequences (up to 100 frames). Built on SDXL with IP-Adapter integration, the framework operates training-free and supports style control (comic, film, realistic) and ControlNet skeleton guidance for precise character pose management.
About 1Prompt1Story
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
Leverages diffusion models with a novel consistency mechanism to generate multi-image sequences that maintain visual coherence across frames without requiring per-image prompts or fine-tuning. Built on PyTorch/Diffusers with Gradio interface support, it includes the Consistory+ benchmark for evaluating cross-image consistency and supports extended narrative generation from single text descriptions.
Scores updated daily from GitHub, PyPI, and npm data. How scores work