DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion
Open accessAbstract
We present DreamPose, a diffusion-based method for generating animated fashion videos from still images. Given an image and a sequence of human body poses, our method synthesizes a video containing both human and fabric motion. To achieve this, we transform a pre-trained text-to-image model (Stable Diffusion [16]) into a pose-and-image guided video synthesis model, using a novel finetuning strategy, a set of architectural changes to support the added conditioning signals, and techniques to encourage temporal consistency. We fine-tune on a collection of fashion videos from the UBC Fashion dataset [50]. We evaluate our method on a variety of clothing styles and poses, and demonstrate that our method produces state-of-the-art results on fashion video animation. Video results are available on our project page: https://grail.cs.washington.edu/projects/dreampose
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
AI is reshaping fashion design through dynamic visuals and supporting the creation of short-form social media videos.
“As AI-generated video capabilities advance, AI is also reshaping fashion design through dynamic visuals [45, 60] and supporting the creation of short-form social media videos [50].”
From Understanding Screenwriters' Practices, Attitudes, and Future Expectations in Human-AI Co-Creation (2025) · cites this paper as [45]
The Results section reports that DreamPose generates fashion videos from still images, supporting the claim about dynamic fashion visuals. The paper does not establish that this reshapes the fashion design process. The short-form social media video claim has a separate citation and is not attributed to this source. (LLM, conf=0.82)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · see citing works
Adding Conditional Control to Text-to-Image Diffusion Models
Zhang, L., Rao, A., & Agrawala, M. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00355 · Cited by 4,547 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Understanding Screenwriters' Practices, Attitudes, and Future Expectations in Human-AI Co-Creation
Tang, Y., Li, H., Lan, M., Ma, X., & Qu, H. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714120 · Cited by 18 · see citing works
“As AI-generated video capabilities advance, AI is also reshaping fashion design through dynamic visuals [45, 60] and supporting the creation of short-form social media videos [50].”
- Authors
- Karras, J., Holynski, A., Wang, T.-C., & Kemelmacher-Shlizerman, I.
- Affiliations
- University of Washington (US)
- Google (United States) (US)
- Nvidia (United Kingdom) (GB)
- Venue
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 22623-22633
- OpenAlex
- W4390874168
- Cited by
- 137
- References
- 2
- Citations by year
- 2026: 21 · 2025: 63 · 2024: 46 · 2023: 7
- FWCI
- 14.68
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- Nvidia
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- Stable Diffusion, diffusion models, temporal coherence, clothing style
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
