Total runs:
1.8K
Run Growth:
699
Growth Rate:
39.83%
Sponsored by
APIMart
FenomAI / LTX-2.3-Multiple-Subject-Reference
Model's Last Updated: June 20 2026
Introduction of LTX-2.3-Multiple-Subject-Reference
Model Details of LTX-2.3-Multiple-Subject-Reference
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
Runs of FenomAI LTX-2.3-Multiple-Subject-Reference on huggingface.co
131
Total runs
0
24-hour runs
24
3-day runs
74
7-day runs
84
30-day runs
More Information About LTX-2.3-Multiple-Subject-Reference huggingface.co Model
Url of LTX-2.3-Multiple-Subject-Reference
LTX-2.3-Multiple-Subject-Reference huggingface.co Url
Provider of LTX-2.3-Multiple-Subject-Reference huggingface.co
Other API from FenomAI
Updated:August 14 2026
Total runs:
1.6K
Run Growth:
-14.3K
Growth Rate:
-889.93%
Total runs:
1.5K
Run Growth:
-2.6K
Growth Rate:
-174.47%
Total runs:
802
Run Growth:
211
Growth Rate:
26.31%
Total runs:
777
Run Growth:
-1.3K
Growth Rate:
-167.70%
Total runs:
504
Run Growth:
-11.9K
Growth Rate:
-2368.25%
Total runs:
421
Run Growth:
-191
Growth Rate:
-45.37%
Total runs:
380
Run Growth:
321
Growth Rate:
84.47%
Total runs:
229
Run Growth:
-71
Growth Rate:
-31.00%
Total runs:
212
Run Growth:
-492
Growth Rate:
-232.08%
Total runs:
182
Run Growth:
-188
Growth Rate:
-103.30%
Total runs:
56
Run Growth:
-125
Growth Rate:
-223.21%
Total runs:
54
Run Growth:
45
Growth Rate:
83.33%
Total runs:
25
Run Growth:
12
Growth Rate:
48.00%
Total runs:
23
Run Growth:
8
Growth Rate:
34.78%
Total runs:
20
Run Growth:
9
Growth Rate:
45.00%
Total runs:
19
Run Growth:
19
Growth Rate:
100.00%
Total runs:
19
Run Growth:
-47
Growth Rate:
-247.37%
Total runs:
16
Run Growth:
-68
Growth Rate:
-425.00%
Total runs:
14
Run Growth:
7
Growth Rate:
50.00%
Total runs:
12
Run Growth:
9
Growth Rate:
75.00%
Total runs:
7
Run Growth:
1
Growth Rate:
14.29%
Total runs:
4
Run Growth:
-2
Growth Rate:
-50.00%
Total runs:
4
Run Growth:
-2
Growth Rate:
-50.00%