Pith. sign in

REVIEW 17 cited by

StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.00330 v2 pith:UV6SWSM6 submitted 2023-12-01 cs.CV cs.AI

Gongye Liu , Menghan Xia , Yong Zhang , Haoxin Chen , Jinbo Xing , Yibo Wang , Xintao Wang , Yujiu Yang
show 1 more author
Ying Shan
This is my paper · ORCID
classification cs.CVcs.AI
keywords stylestylizedadaptergenerationimagereferencestylecraftertext
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Text-to-video (T2V) models have shown remarkable capabilities in generating diverse videos. However, they struggle to produce user-desired stylized videos due to (i) text's inherent clumsiness in expressing specific styles and (ii) the generally degraded style fidelity. To address these challenges, we introduce StyleCrafter, a generic method that enhances pre-trained T2V models with a style control adapter, enabling video generation in any style by providing a reference image. Considering the scarcity of stylized video datasets, we propose to first train a style control adapter using style-rich image datasets, then transfer the learned stylization ability to video generation through a tailor-made finetuning paradigm. To promote content-style disentanglement, we remove style descriptions from the text prompt and extract style information solely from the reference image using a decoupling learning strategy. Additionally, we design a scale-adaptive fusion module to balance the influences of text-based content features and image-based style features, which helps generalization across various text and style combinations. StyleCrafter efficiently generates high-quality stylized videos that align with the content of the texts and resemble the style of the reference images. Experiments demonstrate that our approach is more flexible and efficient than existing competitors.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. High-Resolution Artwork Outpainting with Global Blueprint Guidance and Layout Control

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A two-stage diffusion framework generates a layout-controllable low-resolution blueprint to guide parallel high-resolution artwork outpainting, achieving 2.4× speedup and improved fidelity over sequential baselines.

  2. Neural Scene Designer: Self-Styled Semantic Image Manipulation

    cs.CV 2025-09 conditional novelty 6.0 of 10

    NSD uses a contrastively learned style embedding from the input image itself, fed through a second cross-attention branch, to make diffusion-based inpainting results match the surrounding scene's style.

  3. Calligrapher: Freestyle Text Image Customization

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Calligrapher trains a style encoder and in-context inference on self-distilled FLUX outputs to redraw arbitrary text in the visual style of a reference image.

  4. UNIC: Unified In-Context Video Editing

    cs.CV 2025-06 conditional novelty 6.0 of 10

    One diffusion transformer handles ID insert, swap, delete, stylization, propagation, and re-camera control in a single model using in-context token concatenation with task-aware positional encoding and bias.

  5. VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control

    cs.CV 2025-01 conditional novelty 6.0 of 10

    A zero-shot diffusion framework that inserts a reference object into a video with high-fidelity appearance preservation and precise key-point trajectory motion control.

  6. SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A cross-view attention module and hybrid training recipe let a frozen text-to-video model generate synchronized multi-camera videos from arbitrary viewpoints given only a text prompt and camera poses.

  7. StyleMaster: Stylize Your Video with Artistic Generation and Translation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    StyleMaster improves reference-image video stylization by extracting global and local style separately, training on model-illusion pairs, and adding a motion adapter and gray tile ControlNet.

  8. IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative Models

    cs.CV 2024-12 conditional novelty 6.0 of 10

    An adapter module trained on IQA/IAA scores gives SDXL controllable quality-aware generation, improving perceived quality and enabling reference-based distortion transfer.

  9. FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers

    cs.CV 2025-06 conditional novelty 5.0 of 10

    FullDiT2 accelerates FullDiT-style in-context conditioning for video by dynamic token selection and selective context caching, cutting per-step time by 2-3x with minimal quality loss.

  10. Preliminary Explorations with GPT-4o(mni) Native Image Generation

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A qualitative exploration showing GPT-4o image generation excels at stylization, editing, and personalization but struggles with spatial reasoning, knowledge-based accuracy, and temporal prediction.

  11. Tiger200K: Manually Curated High Visual Quality Video Dataset from UGC Platform

    cs.CV 2025-04 conditional novelty 5.0 of 10

    Tiger200K is a manually curated dataset of 170,000 bilingual-captioned video clips from BiliBili, claimed to have high visual quality for fine-tuning video generation models.

  12. Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion Models

    cs.CV 2025-02 conditional novelty 5.0 of 10

    Masking the image-feature dimensions most correlated with the style reference's content text reduces content leakage and improves text fidelity in text-to-image style transfer diffusion models.

  13. ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning

    cs.CV 2025-01 conditional novelty 5.0 of 10

    A feed-forward multi-concept video customization model that fuses each concept image with its text label and injects the composite embeddings through a separate cross-attention layer, avoiding test-time optimization.

  14. ArtCrafter: Text-Image Aligning Style Transfer via Embedding Reframing

    cs.CV 2025-01 conditional novelty 5.0 of 10

    ArtCrafter improves text-guided style transfer by extracting style with perceiver attention, aligning image and text embeddings, and blending them through explicit modulation.

  15. StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements

    cs.CV 2024-12 conditional novelty 5.0 of 10

    StyleStudio improves text-driven style transfer with cross-modal AdaIN, a negative-style-image classifier-free guidance, and teacher-model layout stabilization.

  16. StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation

    cs.CV 2025-05 reject novelty 4.0 of 10

    StyleAR enables autoregressive image generation models to do style-aligned text-to-image generation using only binary text-image data, via self-reconstruction training and style-enhanced tokens.

  17. Parameter-Efficient Fine-Tuning for Foundation Models

    cs.CL 2025-01 conditional novelty 2.0 of 10

    A survey that categorizes and summarizes parameter-efficient fine-tuning methods across large language, vision, and multimodal models.

Pith tools