- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper presents Custom Forcing, a training-free method for subject customization in autoregressive video generation. It stores reference images and a scene-specific image generated from them as persistent anchors in the KV cache of a frozen video model. To reduce identity drift, drift-adaptive value amplification adjusts the influence of reference features based on the similarity of generated frames to the reference images. Anchor contrast guidance further strengthens reference conditioning by contrasting attention outputs with and without the anchors. Experiments on two autoregressive backbones show improved identity preservation in videos up to two minutes, with comparable motion metrics and moderate inference overhead relative to fixed-anchor conditioning.
Critical strengths
- The paper addresses a practical problem: preserving a specific subject’s identity throughout long autoregressive videos without per-subject fine-tuning.
- The paper is clearly written and easy to follow.
Critical weaknesses
-
The technical novelty is limited. Generating a video keyframe from reference images using an image generation model and inserting it into the autoregressive model’s KV cache is relatively common, as in FashionChameleon [1]. ACG mainly consists of attention extrapolation, L1-norm clipping, and blending, closely resembling NAG [2]. The main change is replacing positive/negative text conditioning with retaining/masking reference anchors. DVA is an adaptation of V-Warper [3].
-
Appendix F.4 reports an average adaptive drift signal of approximately 0.022, while the constant baselines use 0.05, 0.1, and 0.2, corresponding to typical target gains of approximately 1.3 versus at least 3. Thus, the motion degradation of the constant baselines may primarily result from excessive injection strength. This strength mismatch leaves open whether a weaker constant gain or a predefined temporal schedule could achieve similar results, and does not sufficiently establish the necessity of online drift feedback.
-
Comparisons with existing methods are missing. FashionChameleon also performs customized content generation within an autoregressive video framework. I understand that training-free methods cannot be directly compared with training-based methods, but I am interested in how large the performance gap is. Additionally, I would like to see results using human subjects to provide a more intuitive assessment of identity preservation.
[1] FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization [2] Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models [3] V-Warper: Appearance-Consistent Video Diffusion Personalization via Value Warping
Questions for authors
See Critical Weaknesses
4 comments
Response to Reviewer GZgZ (2/2): comparison with existing methods, human subjects
W3. Comparison with existing methods and human subjects.
- FashionChameleon. We agree it is closely related and would have liked to compare directly, but its model weights have not been released. Since you are interested in the gap to training-based methods, we compared Custom Forcing with four models that learn a reference-conditioning module, VACE, MAGREF, Phantom, and 1% Compute, at a common 5.1 s window (App. H.3, Table 17; Table R4). Custom Forcing has the highest DINO-I, equal or higher CLIP-I and prompt adherence, and perceptual quality within 0.041, but it moves less (Dynamic Degree 0.28 vs. 0.46–0.71). We now cite FashionChameleon in App. A.2.
Table R4. Common 5.1 s window, means over 100 videos (Table 17).
| Method | DINO-I | CLIP-I | CLIP-T | Dynamic | Aesth. | Imaging |
|---|---|---|---|---|---|---|
| VACE-1.3B | 0.333 | 0.703 | 0.296 | 0.46 | 0.631 | 0.673 |
| MAGREF-14B | 0.498 | 0.786 | 0.338 | 0.65 | 0.608 | 0.693 |
| Phantom-1.3B | 0.518 | 0.774 | 0.350 | 0.71 | 0.657 | 0.685 |
| 1% Compute | 0.594 | 0.769 | 0.332 | 0.60 | 0.547 | 0.599 |
| Custom Forcing | 0.614 | 0.801 | 0.355 | 0.28 | 0.616 | 0.676 |
- Human subjects (App. H.4, Table 19, Fig. 14; Table R5). We ran the 30 identities of the ConsisID evaluation set (five photos each) with four prompts of our own per identity, at 30 s and 2 min, with all hyperparameters unchanged; the photos are cropped around the face, and DVA uses head masks. Custom Forcing raises face similarity over Custom K/V only by 0.062 at 30 s and 0.074 at 2 min (FaceSim-Arc), with slightly lower FID and comparable CLIPScore, and stays nearly constant as videos get longer (0.204 → 0.192 vs. 0.142 → 0.118). ConsisID, a CogVideoX-5B model fine-tuned on human videos for face identity, reaches much higher face similarity on its 6.1 s clips (0.459 vs. 0.228), so we do not claim parity with face-specialized models (App. G). Custom Forcing is training-free and applies to any subject; its goal is to limit identity drift over long rollouts. Fig. 14 shows three identities over 30 s.
Table R5. Human subjects, official ConsisID metrics (Table 19). ConsisID, by design, takes a single photo (we use image 00); ours takes all five, and our 6.1 s rows are the first 6.1 s of the 30 s videos.
| Method | Span | FaceSim-Arc ↑ | FaceSim-Cur ↑ | FID ↓ | CLIPScore ↑ |
|---|---|---|---|---|---|
| ConsisID | 6.1 s | 0.459 | 0.494 | 173.80 | 31.66 |
| Custom K/V only | 6.1 s | 0.191 | 0.203 | 161.51 | 31.69 |
| Custom Forcing | 6.1 s | 0.228 | 0.241 | 160.62 | 31.82 |
| Custom K/V only | 30 s | 0.142 | 0.152 | 164.17 | 31.58 |
| Custom Forcing | 30 s | 0.204 | 0.216 | 163.97 | 31.56 |
| Custom K/V only | 2 min | 0.118 | 0.127 | 167.77 | 30.85 |
| Custom Forcing | 2 min | 0.192 | 0.201 | 167.71 | 31.24 |
Thank you for the detailed response. The additional experiments address most of my concerns in W2 and W3. However, the contribution remains incremental, and, as the authors acknowledge, performance on human subjects is still limited, which restricts its practical usefulness. On balance, I am raising my recommendation from weak reject to weak accept.
Thank you for your follow-up and updated assessment
Thank you for reviewing our additional results and for raising your score. We are glad that the new experiments addressed your concerns in W2 and W3. Your feedback helped us strengthen our evaluation and clarify our contribution.
We also appreciate your remaining points. We agree that performance on human subjects is still a limitation, and we will discuss it more clearly in the limitations section of the final version as an important direction for future work. We will also make the contribution of Custom Forcing more explicit, as a training-free approach to subject customization for autoregressive video generation.
Thank you again for your time and thoughtful review. Please let us know if you have any further questions before the discussion period ends.
Response to Reviewer GZgZ (1/2): novelty, constant and schedule
Thank you for the careful review and for pointing us to these works. All new results are in the revised PDF (changes in blue). Tables R1–R5 appear in these comments; all other table, figure, section, and appendix numbers refer to the revised PDF. We answer the first two weaknesses here and the third in the next comment.
W1. Novelty. Custom Forcing builds on existing operations, and we credit them. Our contribution is making a frozen autoregressive video model, with its weights unchanged, follow a user-given subject through inference-time control of its KV cache and attention, without customization training; none of the cited methods operates in this setting (Table R1), and each component is designed for it.
Table R1. Relation to the cited works.
W2. Weaker constant and predefined schedule. We ran these controls with all other settings unchanged (App. F.4, Table 13, Fig. 13): a constant b ≡ 0.022 matched to the mean b(t) of DVA, a weaker constant b ≡ 0.01, and a linear schedule with the same mean as DVA. b ≡ 0.022 and the schedule sit near DVA on automated metrics, so we acknowledge them as competitive baselines, while b ≡ 0.01 lowers DINO-I (Table R2). They differ in when they amplify. Please see Fig. 13 in App. F.4 of the revised PDF, which illustrates this distinction. Where little drift is measured, DVA keeps b(t) near zero, while b ≡ 0.022 and the schedule keep amplifying and can enlarge or deform the subject (red boxes), even when their DINO-I is higher (Fig. 13(b)). In a 30 s study, 30 participants ranked the videos of b ≡ 0.022, the schedule, and Custom Forcing for 20 prompts, with ties allowed; Custom Forcing was ranked better than each control more often than worse, for both identity and quality (Holm-adjusted p ≤ 0.009 in all four comparisons; App. D.7, Table 9(d); Table R3).
Table R2. Automated metrics, 30 s, n = 100 (subset of Table 13).
Table R3. Human ranking, 30 s, 30 participants, 20 prompts (Table 9(d)). Share of answers (%) in which Custom Forcing was ranked better than, the same as, or worse than each control; p: mixed-effects logistic regression on the untied answers, Holm-adjusted within each question.