Update README.md

README.md

@@ -10,6 +10,33 @@ github: https://github.com/liconstudio/ComfyUI-Licon-MSR
 library_name: diffusers
 ---
 
+# Licon MSR V2 for LTX-2.3
+
+## What's New in V2
+
+Compared with V1, **Licon MSR V2** introduces significant improvements in three key areas:
+
+### 1. Improved Consistency
+
+- Better preservation of character identity, clothing, objects, and scene details
+- More consistent appearance across frames
+- Improved alignment between multiple reference images and the generated video
+- Reduced identity drift and reference attribute loss
+
+### 2. Improved Stability
+
+- More reliable results across repeated sampling runs
+- Reduced visual artifacts, flickering, and temporal inconsistencies
+- More stable generation in complex multi-subject compositions
+- Improved handling of motion and interactions between subjects
+
+### 3. Improved Scene Logic
+
+- Better understanding of spatial and action relationships described in prompts
+- More natural subject positioning and interaction
+- Improved temporal progression from the beginning to the end of a video
+- More coherent composition of characters, objects, and backgrounds
+
 ## 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.
@@ -22,59 +49,63 @@ This LoRA requires the **[ComfyUI-Licon-MSR](https://github.com/liconstudio/Comf
 
 ### 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
+- **Token-level reference preservation**: Multiple reference images are encoded as video latents, preserving fine-grained visual information at the token level instead of compressing them into a single embedding
+- **Native self-attention retrieval**: Target video tokens directly access reference tokens through the model's existing self-attention mechanism, with no additional architectural components required
+- **In-context conditioning**: References serve as visual memory within the main token sequence rather than 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:
+- **2 to 5 reference images**: Supports varying numbers of reference inputs with increasing composition complexity
+- **Complementary semantic roles**: Each reference image can provide different information:
   - Subject identity
-  - Object/prop details
-  - Scene/background
+  - Object or prop details
+  - Scene or background
   - Local textures
   - Multiple viewpoints
 
-
 ## What It Can Do
 
 ### Identity Preservation Across References
 
-Generate videos where multiple reference identities are simultaneously preserved:
+Generate videos in which multiple reference identities are simultaneously preserved:
+
 - Multiple characters from different reference images
-- Character + object combinations
-- Object + scene compositions
+- Character and object combinations
+- Object and 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)
+Beyond identity preservation, the model can compose references according to textual relationship descriptions:
+
+- Action interactions, such as handing, picking up, or pushing
+- Spatial relationships, such as left and right or foreground and background
+- Temporal event structures, such as 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)
+- Face from reference A and clothing from reference B
+- Object identity from one reference and pose or position from another
+- Background elements from scene references
 
-- **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
+## Usage Tips
 
+- **Prompt description**: Use concise but accurate descriptions of the reference images. Both excessive and insufficient descriptions may reduce consistency.
+- **Reference roles**: Clearly describe the role of each referenced subject, object, or scene in the target video.
+- **High-motion scenes**: 50 fps is recommended for smoother motion coherence.
+- **Sampling**: Complex multi-subject interactions may still benefit from multiple sampling runs.
 
-## Results Showcase
+## V1 vs. V2 Comparison
 
-### V1 Version
+### Comparison 1
 
-| Reference Images | Generated Video |
+| V1 | V2 |
 |:---:|:---:|
-| <img src="validition_v1/01/1.jpg" width="80"> <img src="validition_v1/01/2.jpg" width="80"> <img src="validition_v1/01/bg.png" width="80"> | [▶ Play](validition_v1/01/video.mp4) |
-| <img src="validition_v1/07/1.jpg" width="80"> <img src="validition_v1/07/2.jpg" width="80"> <img src="validition_v1/07/bg.png" width="80"> | [▶ Play](validition_v1/07/video.mp4) |
-| <img src="validition_v1/05/1.png" width="70"> <img src="validition_v1/05/2.png" width="70"> <img src="validition_v1/05/5.png" width="70"> <img src="validition_v1/05/bg.png" width="70"> | [▶ Play](validition_v1/05/video.mp4) |
+| [▶ Play V1](Validition_V2/01/V1_1.mp4) | [▶ Play V2](Validition_V2/01/V2.mp4) |
 
----
+### Comparison 2
+
+| V1 | V2 |
+|:---:|:---:|
+| [▶ Play V1](Validition_V2/02/V1.mp4) | [▶ Play V2](Validition_V2/02/V2.mp4)