ALADDIN: Adversarial Latent Diffusion Distillation for One-Step Identity Swapping

Ivan Shchekotov; Timofei Gritsaev; Viacheslav Pirogov; Dmitry Vetrov

cs.CVOct 27, 2026

ALADDIN: Adversarial Latent Diffusion Distillation for One-Step Identity Swapping

Authors: Ivan Shchekotov, Timofei Gritsaev, Viacheslav Pirogov, Dmitry Vetrov

Organizations: Constructor University, Bremen, Germany · Sumsub, Berlin, Germany

Abstract

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 $G_{\theta_{T}}$ receives the target image $x_{\mathrm{tgt}}$ and the source identity encoded by frozen PuLID, and produces the one-step swap $\hat{x}$ . Identity, pose, expression, and background losses constrain the swap. For adversarial training, the latent of $\hat{x}$ and that of a real image $x^{+}$ are diffused to the same noise level $\sigma$ and passed through a frozen diffusion model; the discriminator, $D_{\varphi}$ , classifies its intermediate features as generated or real. Right (student training) : the frozen teacher constructs the pseudo-target $x_{\mathrm{tgt}}^{A\to B}$ from $x_{\mathrm{src}}^{B}$ and $x_{\mathrm{tgt}}^{A}$ . The student $G_{\theta}$ , initialised from the teacher, swaps identity $A$ back onto this pseudo-target and is supervised toward the real image $x_{\mathrm{tgt}}^{A}$ by the reconstruction loss.

	ID Similarity measured with
Method	MS1M–IR-SE50	Glint–R100	WebFace–R50
Trained against MS1M–IR-SE50
REFace	$0.64^{\dagger}$	0.41	0.39
InfoSwap	$0.58^{\dagger}$	0.43	0.42
Trained against Glint–R100
Ours ALADDIN Student λ=1	0.55	$0.54^{\dagger}$	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.

Panel of Figure 3 — 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 $\downarrow$	ID Sim. $\uparrow$	Retrieval $\uparrow$ Top-1/5	Pose $\downarrow$	Expr. $\downarrow$
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	$\,{}^{\dagger}$ 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 $\downarrow$	ID Sim. $\uparrow$	Pose $\downarrow$	Expr. $\downarrow$
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 $\downarrow$	ID Sim. $\uparrow$	Pose $\downarrow$	Expr. $\downarrow$
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 .

Panel of Figure 4 — 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.

Panel of Figure 5 — 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.

Image Generation

Image generation studies models that create or edit images from text, examples, layouts, and other structured controls.

See all 463 papers

CA-IDD: Cross-Attention Guided Identity-Conditional Diffusion for Identity-Consistent Face Swapping
Apr 27, 2026Md Shohel Rana, Tanoy DebnathImage Generation Identity-Preserving Image Generation
School of Computing
Adaptive Identity Anchoring: Closed-Loop Keyframe Placement for Synthetic Paired Supervision in Video Face Swapping
Jul 23, 2026Logan RobbinsSynthetic Data Augmentation Temporal Consistency in Video Generation
Independent researcher.
From Short Clips to Real-Time Streams: Identity-Aware Supervision and Context-Efficient Generation for Video Face Swapping
Oct 19, 2026Zekai Luo, Yuwei Liang, Ruiqi Ma +8Real-Time Interactive Video Generation Identity-Preserving Video Generation
Zhejiang University · Zhejiang University of Technology

Apr 27, 2026J/K move · Enter open · S save

CA-IDD: Cross-Attention Guided Identity-Conditional Diffusion for Identity-Consistent Face Swapping

Md Shohel Rana, Tanoy Debnath

School of Computing

Image Generation Identity-Preserving Image Generation Diffusion-Based Image Editing Conditional Diffusion Models

Open paper AskPDF arXiv

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.

Abstract

Image Generation

Explore similar work

CA-IDD: Cross-Attention Guided Identity-Conditional Diffusion for Identity-Consistent Face Swapping

Adaptive Identity Anchoring: Closed-Loop Keyframe Placement for Synthetic Paired Supervision in Video Face Swapping

From Short Clips to Real-Time Streams: Identity-Aware Supervision and Context-Efficient Generation for Video Face Swapping