Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.08061 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915611892776960 |
|---|---|
| author | Singhania, Aditi Jain, Arushi Malani, Krutik Dhawan, Riddhi Chakraborty, Souymodip Batra, Vineet Phogat, Ankit |
| author_facet | Singhania, Aditi Jain, Arushi Malani, Krutik Dhawan, Riddhi Chakraborty, Souymodip Batra, Vineet Phogat, Ankit |
| contents | Subject-driven image generation aims to synthesize novel depictions of a specific subject across diverse contexts while preserving its core identity features. Achieving both strong identity consistency and high prompt diversity presents a fundamental trade-off. We propose a LoRA fine-tuned diffusion model employing a latent concatenation strategy, which jointly processes reference and target images, combined with a masked Conditional Flow Matching (CFM) objective. This approach enables robust identity preservation without architectural modifications. To facilitate large-scale training, we introduce a two-stage Distilled Data Curation Framework: the first stage leverages data restoration and VLM-based filtering to create a compact, high-quality seed dataset from diverse sources; the second stage utilizes these curated examples for parameter-efficient fine-tuning, thus scaling the generation capability across various subjects and contexts. Finally, for filtering and quality assessment, we present CHARIS, a fine-grained evaluation framework that performs attribute-level comparisons along five key axes: identity consistency, prompt adherence, region-wise color fidelity, visual quality, and transformation diversity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08061 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Taming Identity Consistency and Prompt Diversity in Diffusion Models via Latent Concatenation and Masked Conditional Flow Matching Singhania, Aditi Jain, Arushi Malani, Krutik Dhawan, Riddhi Chakraborty, Souymodip Batra, Vineet Phogat, Ankit Computer Vision and Pattern Recognition Artificial Intelligence Subject-driven image generation aims to synthesize novel depictions of a specific subject across diverse contexts while preserving its core identity features. Achieving both strong identity consistency and high prompt diversity presents a fundamental trade-off. We propose a LoRA fine-tuned diffusion model employing a latent concatenation strategy, which jointly processes reference and target images, combined with a masked Conditional Flow Matching (CFM) objective. This approach enables robust identity preservation without architectural modifications. To facilitate large-scale training, we introduce a two-stage Distilled Data Curation Framework: the first stage leverages data restoration and VLM-based filtering to create a compact, high-quality seed dataset from diverse sources; the second stage utilizes these curated examples for parameter-efficient fine-tuning, thus scaling the generation capability across various subjects and contexts. Finally, for filtering and quality assessment, we present CHARIS, a fine-grained evaluation framework that performs attribute-level comparisons along five key axes: identity consistency, prompt adherence, region-wise color fidelity, visual quality, and transformation diversity. |
| title | Taming Identity Consistency and Prompt Diversity in Diffusion Models via Latent Concatenation and Masked Conditional Flow Matching |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.08061 |