Buckets:

---

dapangwoshi

/

LTX-2.3-Multiple-Subject-Reference-bucket

Overview

This model implements a novel approach to multi-reference video generation using Multiple Subject Reference (MSR). Instead of introducing additional encoder branches or fusion modules, we transform multiple static reference images into a pseudo-video sequence that shares the same representation space as the target video.

Usage

This LoRA requires the ComfyUI-Licon-MSR plugin for ComfyUI. A sample workflow is included in the model files for easy testing and experimentation.

Key Features

Multi-Reference Visual Memory

• Token-level reference preservation: Multiple reference images are encoded as video latents, preserving fine-grained visual information at token level rather than compressing into a single embedding
• Native self-attention retrieval: The target video tokens directly access reference tokens through the model's existing self-attention mechanism—no new architectural components needed
• In-context conditioning: References serve as "visual memory" within the main token sequence, not as external conditioning inputs

Flexible Reference Composition

• 2 to 5 reference images: Supports varying numbers of reference inputs with increasing complexity
• Complementary semantic roles: Each reference image can carry different information:
  • Subject identity
  • Object/prop details
  • Scene/background
  • Local textures
  • Multiple viewpoints

What It Can Do

Identity Preservation Across References

Generate videos where multiple reference identities are simultaneously preserved:

• Multiple characters from different reference images
• Character + object combinations
• Object + scene compositions

Relation-Based Composition

Beyond mere identity preservation, the model can compose references based on textual relation descriptions:

• Action interactions (handing, picking up, pushing)
• Spatial relationships (left-right, foreground-background)
• Temporal event structures (start → process → result)

Cross-Reference Attribute Selection

The model learns to selectively retrieve attributes from different references:

• Face from reference A, clothing from reference B
• Object identity from one reference, pose/position from another
• Background elements from scene references

Usage Tips (V1 Version)

• Prompt description: Requires concise but accurate description of reference images. Over-description or under-description both lead to consistency degradation
• High-motion scenes: 50fps recommended to ensure smooth motion coherence
• Generation reliability: Typically requires 2-3 sampling runs to achieve accurate results

Results Showcase

V1 Version

Reference Images	Generated Video
	▶ Play
	▶ Play
	▶ Play