Face swapping transfers a source identity onto a target image while preserving the target's pose, expression, hair, and lighting. The most realistic current methods are diffusion-based, but they need many network evaluations per image. GAN-based methods are fast, yet trained from scratch they must learn realism from the adversarial signal alone and produce visibly weaker results. We present ALADDIN (Adversarial Latent Diffusion Distillation for One-Step Identity Swapping), a one-step face swapper obtained by initialising the generator from a pre-trained multi-step flow-matching model and training it adversarially under identity and target-preservation constraints. We expose a controllable trade-off between identity transfer and target-attribute preservation by training a student model with triplet pseudo-label supervision. We additionally identify a bias in the standard evaluation protocol, which favours methods trained against the same identity encoder used to score them, and re-evaluate all baselines with an independent one. ALADDIN is state-of-the-art among one-step methods in realism and target preservation at comparable identity transfer, and matches the best multi-step model with 28 times fewer network evaluations and an order of magnitude fewer training pairs.
Figures & tables
Figure 2: Overview of ALADDIN training. Left (teacher training) : the teacher generator GθT receives the target image xtgt and the source identity encoded by frozen PuLID, and produces the one-step swap x^ . Identity, pose, expression, and background losses constrain the swap. For adversarial training, the latent of x^ and that of a real image x+ are diffused to the same noise level σ and passed through a frozen diffusion model; the discriminator, Dφ , classifies its intermediate features as generated or real. Right (student training) : the frozen teacher constructs the pseudo-target xtgtA→B from xsrcB and xtgtA . The student Gθ , initialised from the teacher, swaps identity A back onto this pseudo-target and is supervised toward the real image xtgtA by the reconstruction loss.
ID Similarity measured with
Method
MS1M–IR-SE50
Glint–R100
WebFace–R50
Trained against MS1M–IR-SE50
REFace
0.64†
0.41
0.39
InfoSwap
0.58†
0.43
0.42
Trained against Glint–R100
Ours ALADDIN Student λ=1
0.55
0.54†
0.50
Table 1: Identity encoder bias in prior evaluation protocols . Each method is scored by all three ArcFace identity encoders. † marks the identity encoder the method is trained against.
Figure 3: Qualitative comparison on selected FFHQ source–target pairs. The first two columns give the source and the target; the remaining columns show the swap produced by each method. Every row probes a different difficulty. Naturalness transfers an identity onto a target with unusual hair, and Age presents a large age gap between source and target. The last four rows test how well the target’s attributes survive the swap: glasses, tattoo, head pose, and facial expression.
Method
FID ↓
ID Sim. ↑
Retrieval ↑ Top-1/5
Pose ↓
Expr. ↓
One-step methods
MegaFS
15.54
0.38
84.5/89.7
4.50
1.14
E4S
12.00
0.37
77.9/87.9
4.47
1.30
HiFiFace
11.08
0.45
93.1/96.7
3.20
1.34
InSwapper †
8.67
† 0.60
90.3/90.5
2.80
1.52
CSCS
8.59
0.63
99.4 / 100
3.70
1.45
Table 2: Results on 1,000 pairs from FFHQ . FID is computed on CLIP ViT-B/32 features (Section 4 ). Identity similarity and retrieval are measured with WebFace–R50 . Retrieval reports top-1 and top-5 accuracy in percent. Methods are ordered by FID within each group, with better FID placed lower. Bold shows the best value in each column; the second and third best are underlined .
FID ↓
ID Sim. ↑
Pose ↓
Expr. ↓
Data mixture ratio (cross / same ID)
1.00 / 0.00
5.50
0.49
2.20
0.95
0.75 / 0.25, optimal ALADDIN Teacher
4.55
0.49
1.90
0.77
0.50 / 0.50
5.01
0.49
1.87
0.79
Discriminator input
Raw latent
20.46
0.53
2.82
1.13
Table 3: Ablation study of the teacher training . FID is computed on CLIP ViT-B/32 features. Identity similarity is measured with WebFace–R50 under the masked protocol of Table 2 . The optimal configuration, 0.75 / 0.25, is the one we report as ALADDIN Teacher. The discriminator ablation keeps the 1.00 / 0.00 mixture to isolate the effect of the discriminator input. Checkpoints are selected to match identity similarity (Appendix A ), so that column is not ranked. Bold shows the best value in each remaining column and the second best is underlined .
Appendix figures & tables3 assets
Supplementary material from the paper’s appendix.
Appendix
Method
FID ↓
ID Sim. ↑
Pose ↓
Expr. ↓
One-step methods
MegaFS
15.54
0.48
4.50
1.14
E4S
12.00
0.49
4.47
1.30
HiFiFace
11.08
0.48
3.20
1.34
InSwapper
8.67
0.56
2.80
1.52
CSCS
8.59
0.61
3.70
1.45
Appendix
Table 4: Results on 1,000 pairs from FFHQ with the previous, biased protocol. Identity metric is scored with MS1M–IR-SE50 . FID (CLIP ViT-B/32 features), pose, and expression follow the protocol of Table 2 ; only the identity evaluator is changed. Methods are ordered by FID within each group, with better FID placed lower. Bold shows the best value in each column; the second and third best are underlined .
Figure 4: Qualitative comparison on selected FFHQ source–target pairs. The first two columns give the source and the target; the remaining columns show the swap produced by each method. Every row probes a different difficulty. Gender transfers an identity onto a target of another perceived gender. Skin tone presents a source–target pair with markedly different skin tones. Piercing tests piercing transfer from the target. Source glasses tests that a method does not transfer glasses from the source.
Figure 5: Qualitative comparison on selected FFHQ source–target pairs for the methods omitted from Figure 3 . The first two columns give the source and the target; the remaining columns show the swap produced by each method. Every row probes a different difficulty. Naturalness transfers an identity onto a target with unusual hair, and Age presents a large age gap between source and target. The last four rows test how well the target’s attributes survive the swap: glasses, tattoo, head pose, and facial expression.
Face swapping aims to optimize realistic facial image generation by leveraging the identity of a source face onto a target face while preserving pose, expression, and context. However, existing methods, especially GAN-based methods, often struggle to balance identity preservation and visual realism due to limited controllability and mode collapse. In this paper, we introduce CA-IDD (Cross-Attention Guided Identity-Conditional Diffusion), the first diffusion-based face swapping approach that integrates multi-modal guidance comprising gaze, identity, and facial parsing through multi-scale cross-attention. Precomputed identity embeddings are incorporated into the denoising process via hierarchical attention layers, resulting in accurate and consistent identity transfer. To improve semantic coherence and visual quality, we use expert-guided supervision, with facial parsing and gaze-consistency modules. Unlike GAN-based or implicit-fusion methods, our diffusion framework provides stable training, robust generalization, and spatially adaptive identity alignment, allowing for fine-grained regional control across pose and expression variations. CA-IDD achieves an FID of 11.73, exceeding established baselines such as FaceShifter and MegaFS. Qualitative results also reveal improved identity retention across diverse poses, establishing CA-IDD as a strong foundation for future diffusion-based face editing.
Video face swapping has no natural paired supervision: no real footage exists of one person's face performing another person's video. The strongest current answer, DreamID-V's SyncID-Pipe, mints pairs by replacing the identity in exactly two frames of a real clip -- the first and the last -- and regenerating the rest from a pose sequence alone. Pose carries no appearance evidence of the swapped-in identity, so over long clips, occlusions, and extreme pose excursions the synthesized identity has a long unanchored span on which to drift; no published ablation examines anchor count or placement. We propose Adaptive Identity Anchoring (AIA): (i) generalize the synthesizer to arbitrary anchor sets, architecturally natural for diffusion-forcing-style transformers where conditioning on a frame is clamping its tokens to zero noise; (ii) place anchors by a closed feedback loop that scores every generated frame against the real reference identity and inserts an image-face-swapped anchor at the worst-scoring frame until the pair passes a threshold or exhausts a budget; (iii) reuse the loop's verdict as an automatic data filter. A second pathology, the beauty-filter look of over-smoothed skin, has the same root cause: micro-texture, like identity, is priced by none of the pipeline's objectives. We therefore pair AIA with Reality-Referenced Texture Restoration: matched re-graining from each real frame's non-face regions, band-split transfer of sub-identity micro-texture from the real footage, and a second, spectral acceptance channel refereed by the footage's own spectrum. Identity-anchor density, we argue, is a controllable quality dial, and we specify falsifiable experiments -- drift-versus-gap curves, uniform-versus-adaptive placement at matched budgets, student training on AIA-minted data, and texture ablations with a human beauty-filter study -- that would validate or refute the proposal.
Video face swapping transfers the reference identity to a target video while preserving its other attributes and motion. Despite recent progress in reference-guided flow-based methods, jointly achieving faithful identity transfer, high fidelity, and real-time generation over long video streams remains challenging. To address this challenge, we rethink the task-specific structure of reference-guided video face swapping. First, face swapping changes only identity while preserving most visual content, yet flow-matching supervision is weakly sensitive to these changes. We therefore develop Joint Rec-ID Loss, which balances explicit identity supervision and latent reconstruction according to the noise level. Second, the target video already provides non-edited attributes and temporal dynamics, enabling generation with fewer spatial tokens and shorter temporal contexts through Face-RoI Generation and Short-Context Rollout Training. By integrating these designs, we propose StreamingSwap, a reference-guided flow-matching framework for real-time streaming video face swapping. We also introduce HumanFaceVid, comprising 1,000 hours of cinematic training data and evaluation sets of 200 short and 200 long videos. Experiments demonstrate that our method achieves competitive identity transfer and visual quality at 20 FPS on a single NVIDIA RTX 4090 GPU, with stable generation over videos up to 10 minutes long. Project webpage: https://aim-uofa.github.io/StreamingSwap/
Zekai Luo, Yuwei Liang, Ruiqi Ma +8
Zhejiang University · Zhejiang University of Technology