Collaborative Diffusion for Multi-Modal Face Generation and Editing
Open accessThe DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Abstract
Diffusion models arise as a powerful generative tool recently. Despite the great progress, existing diffusion models mainly focus on uni-modal control, i.e., the diffusion process is driven by only one modality of condition. To further unleash the users' creativity, it is desirable for the model to be controllable by multiple modalities simultaneously, e.g. generating and editing faces by describing the age (text-driven) while drawing the face shape (mask-driven). In this work, we present Collaborative Diffusion, where pre-trained uni-modal diffusion models collaborate to achieve multi-modal face generation and editing without re-training. Our key insight is that diffusion models driven by different modalities are inherently complementary regarding the latent denoising steps, where bilateral connections can be established upon. Specifically, we propose dynamic diffuser, a meta-network that adaptively hallucinates multimodal denoising steps by predicting the spatial-temporal influence functions for each pre-trained uni-modal model. Collaborative Diffusion not only collaborates generation capabilities from uni-modal diffusion models, but also integrates multiple uni-modal manipulations to perform multi-modal editing. Extensive qualitative and quantitative experiments demonstrate the superiority of our framework in both image quality and condition consistency.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00813 · Cited by 6,332
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2019) · arXiv · doi:10.48550/arxiv.1912.04958 · Cited by 6,332
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2017) · arXiv · doi:10.48550/arxiv.1710.10196 · Cited by 4,727
Diffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., & Metaxas, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.629 · Cited by 3,021
Semantic Image Synthesis With Spatially-Adaptive Normalization
Park, T., Liu, M.-Y., Wang, T.-C., & Zhu, J.-Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00244 · Cited by 2,974 · cited 1×
“Conditional generation [10, 11, 13, 31, 34, 37, 40, 43–46, 51, 65, 67–71] and editing [8, 32, 41, 53, 54, 67, 68] is an active line of research focusing on conditioning generative models on different modalities, such as texts [24, 41, 67, 68], segmentation masks [32, 33, 40, 47], and audios [59].”
BackgroundNeural Discrete Representation Learning
Oord, A. V. D., Vinyals, O., & Kavukcuoglu, K. (2017) · arXiv · doi:10.48550/arxiv.1711.00937 · Cited by 2,729
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., & Ganguli, S. (2015) · arXiv · doi:10.48550/arxiv.1503.03585 · Cited by 2,637 · cited 2×
“Recent years have witnessed substantial progress in image synthesis and editing with the surge of diffusion models [11, 23, 62, 64].”
BackgroundPhotorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E., Ghasemipour, S. K. S., Ayan, B. K., Mahdavi, S. S., Lopes, R. G., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.11487 · Cited by 2,528 · cited 1×
“In addition to the remarkable synthesis quality, one appealing property of diffusion models is the flexibility of conditioning on various modalities, such as texts [3, 16, 29, 30, 39, 48, 51], segmentation masks [48, 65, 66], and sketches [7, 65].”
BackgroundTaming Transformers for High-Resolution Image Synthesis
Esser, P., Rombach, R., & Ommer, B. (2020) · arXiv · doi:10.48550/arxiv.2012.09841 · Cited by 2,514
Taming Transformers for High-Resolution Image Synthesis
Esser, P., Rombach, R., & Ommer, B. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01268 · Cited by 2,514 · cited 2×
“The learned codebook is then sampled, either sequentially [12, 61] or parallelly [5, 6, 16], for synthesis.”
BackgroundMethodHierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511
Denoising Diffusion Implicit Models
Song, J., Meng, C., & Ermon, S. (2020) · arXiv · doi:10.48550/arxiv.2010.02502 · Cited by 2,507 · cited 1×
“Existing works focus on improving the performance and efficiency of diffusion models through enhanced architecture designs [19,53] and sampling schemes [63].”
BackgroundGenerative Adversarial Text to Image Synthesis
Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., & Lee, H. (2016) · arXiv · doi:10.48550/arxiv.1605.05396 · Cited by 2,494
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2022) · arXiv · doi:10.48550/arxiv.2208.12242 · Cited by 2,442
Zero-shot text-to-image generation
Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., & Sutskever, I. (2021) · arXiv · doi:10.48550/arxiv.2102.12092 · Cited by 2,417
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02155 · Cited by 2,295 · cited 1×
“It is then fixed and combined with existing face editing approaches [29, 50] for multi-modal editing.”
BackgroundScore-Based Generative Modeling through Stochastic Differential Equations
Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2020) · arXiv · doi:10.48550/arxiv.2011.13456 · Cited by 1,953
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
Xu, T., Zhang, P., Huang, Q., Zhang, H., Gan, Z., Huang, X., & He, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00143 · Cited by 1,923
Image Super-Resolution Via Iterative Refinement
Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D. J., & Norouzi, M. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3204461 · Cited by 1,829
Image Super-Resolution via Iterative Refinement
Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D. J., & Norouzi, M. (2021) · arXiv · doi:10.48550/arxiv.2104.07636 · Cited by 1,829
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., & Chen, M. (2021) · arXiv · doi:10.48550/arxiv.2112.10741 · Cited by 1,357 · cited 1×
“In addition to the remarkable synthesis quality, one appealing property of diffusion models is the flexibility of conditioning on various modalities, such as texts [3, 16, 29, 30, 39, 48, 51], segmentation masks [48, 65, 66], and sketches [7, 65].”
BackgroundInterpreting the Latent Space of GANs for Semantic Face Editing
Shen, Y., Gu, J., Tang, X., & Zhou, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00926 · Cited by 1,063
A Connection Between Score Matching and Denoising Autoencoders
Vincent, P. (2011) · Neural Computation · doi:10.1162/neco_a_00142 · Cited by 1,011 · cited 1×
“In the diffusion-based framework, models are trained with score-matching objectives [22, 64] at various noise levels, and sampling is done via iterative denoising.”
Method(2005) · doi:10.5555/1046920.1088696 · Cited by 756
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2021) · arXiv · doi:10.48550/arxiv.2112.10752 · Cited by 737
Vector Quantized Diffusion Model for Text-to-Image Synthesis
Gu, S., Chen, D., Bao, J., Wen, F., Zhang, B., Chen, D., Yuan, L., & Guo, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01043 · Cited by 720
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation
Kim, G., Kwon, T., & Ye, J. C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00246 · Cited by 570
Cascaded Diffusion Models for High Fidelity Image Generation
Ho, J., Saharia, C., Chan, W., Fleet, D. J., Norouzi, M., & Salimans, T. (2021) · arXiv · doi:10.48550/arxiv.2106.15282 · Cited by 514
CogView: Mastering Text-to-Image Generation via Transformers
Ding, M., Yang, Z., Hong, W., Zheng, W., Zhou, C., Yin, D., Lin, J., Zou, X., Shao, Z., Yang, H., et al. (2021) · arXiv · doi:10.48550/arxiv.2105.13290 · Cited by 450
MaskGIT: Masked Generative Image Transformer
Chang, H., Zhang, H., Jiang, L., Liu, C., & Freeman, W. T. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01103 · Cited by 446 · cited 1×
“The learned codebook is then sampled, either sequentially [12, 61] or parallelly [5, 6, 16], for synthesis.”
MethodImagen Video: High Definition Video Generation with Diffusion Models
Ho, J., Chan, W., Saharia, C., Whang, J., Gao, R., Gritsenko, A., Kingma, D. P., Poole, B., Norouzi, M., Fleet, D. J., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.02303 · Cited by 399
Make-A-Video: Text-to-Video Generation without Text-Video Data
Singer, U., Polyak, A., Hayes, T., Yin, X., An, J., Zhang, S., Hu, Q., Yang, H., Ashual, O., Gafni, O., et al. (2022) · arXiv · doi:10.48550/arxiv.2209.14792 · Cited by 395
TediGAN: Text-Guided Diverse Face Image Generation and Manipulation
Xia, W., Yang, Y., Xue, J.-H., & Wu, B. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00229 · Cited by 376 · cited 4×
“Method FID ↓ Text (%) ↑ Mask (%) ↑ TediGAN [74, 75] 157.”
BackgroundMethodInfluentialMake-A-Scene: Scene-Based Text-to-Image Generation with Human Priors
Gafni, O., Polyak, A., Ashual, O., Sheynin, S., Parikh, D., & Taigman, Y. (2022) · arXiv · doi:10.48550/arxiv.2203.13131 · Cited by 332
Compositional Visual Generation with Composable Diffusion Models
Liu, N., Li, S., Du, Y., Torralba, A., & Tenenbaum, J. B. (2022) · arXiv · doi:10.48550/arxiv.2206.01714 · Cited by 295
SegDiff: Image Segmentation with Diffusion Probabilistic Models
Amit, T., Shaharbany, T., Nachmani, E., & Wolf, L. (2021) · arXiv · doi:10.48550/arxiv.2112.00390 · Cited by 179 · cited 1×
“Diffusion models [20, 56, 58] have recently become a mainstream approach for image synthesis [9, 11, 38] apart from Generative Adversarial Networks (GANs) [14], and success has also been found in various domains including video generation [17, 19, 55, 63], image restoration [21, 52], semantic segmentation [1, 4, 15],…”
BackgroundPhenaki: Variable Length Video Generation From Open Domain Textual Description
Villegas, R., Babaeizadeh, M., Kindermans, P.-J., Moraldo, H., Zhang, H., Saffar, M. T., Castro, S., Kunze, J., & Erhan, D. (2022) · arXiv · doi:10.48550/arxiv.2210.02399 · Cited by 92 · cited 1×
“Diffusion models [20, 56, 58] have recently become a mainstream approach for image synthesis [9, 11, 38] apart from Generative Adversarial Networks (GANs) [14], and success has also been found in various domains including video generation [17, 19, 55, 63], image restoration [21, 52], semantic segmentation [1, 4, 15],…”
Background
Cited by
Face Generation and Editing With StyleGAN: A Survey
Melnik, A., Miasayedzenkau, M., Makaravets, D., Pirshtuk, D., Akbulut, E., Holzmann, D., Renusch, T., Reichert, G., & Ritter, H. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3350004 · Cited by 105
Diffusion Facial Forgery Detection
Cheng, H., Guo, Y., Wang, T., Nie, L., & Kankanhalli, M. (2024) · Proceedings of the 32nd ACM International Conference on Multimedia · doi:10.1145/3664647.3680797 · Cited by 47
“In contrast to the above unconditional approaches, recent diffusion models have shifted their focus toward conditional image synthesis [7, 26, 50, 54, 74, 76].”
Zhang, X., Wang, Q., Li, M., Yuan, Y., Xiao, M., Zhuang, F., & Yu, D. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3629066 · Cited by 15
“Diffusion models are a class of generative models based on Markov processes that have demonstrated exceptional performance in the generation of data in various domains, including images [19], voice [34], and time series [47].”
Metadata
- Authors
- Huang, Z., Chan, K. C. K., Jiang, Y., & Liu, Z.
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 6080-6090
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386075893
- Cited by
- 147
- References
- 44
- FWCI
- 16.71
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.