# DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning arXiv: https://arxiv.org/abs/2504.14509 ยท HTML: https://mlsanity.com/paper/2504.14509/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. - Builds on 28 of its 41 references that are in the map. - First posted on arXiv 20 Apr 2025. ## Placed in - Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/) ## Builds on (most cited first, 28 of 28) - [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022) - [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022) - [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018) - [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019) - [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023) - [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023) - [Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://mlsanity.com/paper/2311.17117/) (2023) - [Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set](https://mlsanity.com/paper/1903.08527/) (2019) - [SimSwap: An Efficient Framework For High Fidelity Face Swapping](https://mlsanity.com/paper/2106.06340/) (2021) - [PuLID: Pure and Lightning ID Customization via Contrastive Alignment](https://mlsanity.com/paper/2404.16022/) (2024) - [HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation](https://mlsanity.com/paper/2004.00060/) (2020) - [One Shot Face Swapping on Megapixels](https://mlsanity.com/paper/2105.04932/) (2021) - [Arc2Face: A Foundation Model for ID-Consistent Human Faces](https://mlsanity.com/paper/2403.11641/) (2024) - [HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping](https://mlsanity.com/paper/2106.09965/) (2021) - [DiffFace: Diffusion-based Face Swapping with Facial Guidance](https://mlsanity.com/paper/2212.13344/) (2022) - [Fine-Grained Face Swapping via Regional GAN Inversion](https://mlsanity.com/paper/2211.14068/) (2022) - [Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control](https://mlsanity.com/paper/2405.12970/) (2024) - [High-resolution Face Swapping via Latent Semantics Disentanglement](https://mlsanity.com/paper/2203.15958/) (2022) - [Region-Aware Face Swapping](https://mlsanity.com/paper/2203.04564/) (2022) - [FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping](https://mlsanity.com/paper/2210.10473/) (2022) - [StyleSwap: Style-Based Generator Empowers Robust Face Swapping](https://mlsanity.com/paper/2209.13514/) (2022) - [3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation](https://mlsanity.com/paper/2312.00311/) (2023) - [Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models](https://mlsanity.com/paper/2409.07269/) (2024) - [AltDiffusion: A Multilingual Text-to-Image Diffusion Model](https://mlsanity.com/paper/2308.09991/) (2023) - [Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data](https://mlsanity.com/paper/2203.10474/) (2022) - [ReliableSwap: Boosting General Face Swapping Via Reliable Supervision](https://mlsanity.com/paper/2306.05356/) (2023) ## Built on by (most cited first, 10 of 10) - [Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning](https://mlsanity.com/paper/2508.21048/) (2025) - [DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer](https://mlsanity.com/paper/2601.01425/) (2026) - [OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer](https://mlsanity.com/paper/2601.14250/) (2026) - [Why Fake ? Unveiling the Semantic Vocabulary of Deepfake Detectors](https://mlsanity.com/paper/2607.07216/) (2026) - [DirectSwap: Paired, Mask-Free Video Head Swapping with Full-Reference Evaluation](https://mlsanity.com/paper/2512.09417/) (2025) - [APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping](https://mlsanity.com/paper/2601.15288/) (2026) - [Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement](https://mlsanity.com/paper/2602.18752/) (2026) - [UniBioTransfer: A Unified Framework for Multiple Biometrics Transfer](https://mlsanity.com/paper/2603.19637/) (2026) - [Generative Anonymization in Event Streams](https://mlsanity.com/paper/2604.12803/) (2026) - [Adaptive Identity Anchoring: Closed-Loop Keyframe Placement for Synthetic Paired Supervision in Video Face Swapping](https://mlsanity.com/paper/2607.21434/) (2026) ## Abstract (arXiv) In this paper, we introduce DreamID, a diffusion-based face swapping model that achieves high levels of ID similarity, attribute preservation, image fidelity, and fast inference speed. Unlike the typical face swapping training process, which often relies on implicit supervision and struggles to achieve satisfactory results. DreamID establishes explicit supervision for face swapping by constructing Triplet ID Group data, significantly enhancing identity similarity and attribute preservation. The iterative nature of diffusion models poses challenges for utilizing efficient image-space loss functions, as performing time-consuming multi-step sampling to obtain the generated image during training is impractical. To address this issue, we leverage the accelerated diffusion model SD Turbo, reducing the inference steps to a single iteration, enabling efficient pixel-level end-to-end training with explicit Triplet ID Group supervision. Additionally, we propose an improved diffusion-based model architecture comprising SwapNet, FaceNet, and ID Adapter. This robust architecture fully unlocks the power of the Triplet ID Group explicit supervision. Finally, to further extend our method, we explicitly modify the Triplet ID Group data during training to fine-tune and preserve specific attributes, such as glasses and face shape. Extensive experiments demonstrate that DreamID outperforms state-of-the-art methods in terms of identity similarity, pose and expression preservation, and image fidelity. Overall, DreamID achieves high-quality face swapping results at 512*512 resolution in just 0.6 seconds and performs exceptionally well in challenging scenarios such as complex lighting, large angles, and occlusions.