The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index; 1 of the 5 sources its claims cite were checked for support.
Scalable Diffusion Models with Transformers
Open accessAbstract
We explore a new class of diffusion models based on the transformer architecture. We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the scalability of our Diffusion Transformers (DiTs) through the lens of forward pass complexity as measured by Gflops. We find that DiTs with higher Gflops—through increased transformer depth/width or increased number of input tokens—consistently have lower FID. In addition to possessing good scalability properties, our largest DiT-XL/2 models outperform all prior diffusion models on the class-conditional ImageNet 512×512 and 256×256 benchmarks, achieving a state-of-the-art FID of 2.27 on the latter.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
Diffusion Transformers (DiTs) replace the standard U-Net backbone in latent diffusion models with a transformer operating on latent patches. DiT-XL/2 achieves state-of-the-art class-conditional ImageNet generation, reaching FID 2.27 at 256×256 and 3.04 at 512×512.
Key findings
- DiT block conditioning matters: adaLN-Zero outperforms cross-attention and in-context conditioning at all training stages while being the most compute-efficient; at 400K iterations its FID is nearly half that of the in-context model.
- Scaling DiT Gflops improves sample quality: across 12 models, transformer Gflops and FID-50K at 400K steps have a correlation of −0.93, with gains from increasing depth/width or number of input tokens.
- DiT-XL/2 sets state of the art: FID 2.27 on class-conditional ImageNet 256×256 with classifier-free guidance cfg=1.50, improving on LDM’s previous best 3.60; at 512×512 it reaches FID 3.04 versus ADM’s 3.85.
- Larger DiT models are more compute-efficient, and extra sampling compute cannot compensate for smaller models: DiT-L/2 with 1000 sampling steps uses 80.7 Tflops and gets FID-10K 25.9, while DiT-XL/2 with 128 steps uses 15.2 Tflops and gets FID-10K 23.7.
Methods
- Design: latent diffusion with a frozen off-the-shelf Stable Diffusion VAE (downsample factor 8); DiT patchifies latents, applies ViT-style positional embeddings, processes tokens through N transformer blocks, and linearly decodes to noise and covariance predictions. Design space includes patch sizes p=2,4,8; block variants in-context, cross-attention, adaLN, and adaLN-Zero; model sizes DiT-S/B/L/XL.
- Data and training: class-conditional ImageNet at 256×256 and 512×512; AdamW, constant learning rate 1×10⁻⁴, batch size 256, horizontal flips, EMA decay 0.9999, no learning-rate warmup or regularization; diffusion hyperparameters retained from ADM; implemented in JAX on TPU-v3 pods.
- Evaluation: FID-50K with 250 DDPM sampling steps using ADM’s TensorFlow evaluation suite; 12 DiT models swept over S/B/L/XL and p=8/4/2 at 400K steps; DiT-XL/2 trained for 7M steps at 256×256 and 3M steps at 512×512; additional comparisons of conditioning strategies and model versus sampling compute.
Limitations
- The paper does not state an explicit limitations section.
- Evident from the text: experiments are limited to class-conditional ImageNet at 256×256 and 512×512; text-to-image and other domains are left to future work.
- Evident from the text: DiTs use a frozen off-the-shelf VAE, so generation quality depends on that VAE; training hyperparameters were retained from ADM and not tuned; pixel-space DiT is mentioned as possible but not tested.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
28 Own result · 5 Own interpretation · 4 No basis given · 3 Sources not found · 2 Own method · 1 Partly supported · 1 Not checked yet · accuracy not yet measured
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“As shown in Figure 2, LDMs achieve good performance while using a fraction of the Gflops of pixel space diffusion models like ADM.”
§ 3. Diffusion Transformers > 3.1. Preliminaries
What the sources say
- Partly supportedcites [48] sourceExperimental — accuracy not yet measured
Section 4.2 reports performance close to ADM on LSUN-Bedrooms while using four times fewer training resources, and Appendix D.4 describes competitive ImageNet performance with lower compute requirements. These passages support the performance-and-efficiency comparison, but our copy does not give a GFLOPs comparison with ADM; it reports training resources instead. (LLM, conf=0.85)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Larger DiT models are more compute-efficient.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Adaptive layer norm works best.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Transformer Gflops are strongly correlated with FID.”
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Performance steadily improves in FID as model flops increase.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing transformer forward pass Gflops increases sample quality.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The results demonstrate that different DiT configs obtain similar FID values when their total Gflops are similar (e.g., DiT-S/2 and DiT-B/4).”
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Indeed, scaling both model size and the number of tokens yields notable improvements in visual quality.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Across all four configs, significant improvements in FID are obtained over all stages of training by making the transformer deeper and wider.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Scaling the transformer backbone yields better generative models across all model sizes and patch sizes.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- The quote only partly states this claim. 4
- Probably not a substantial claim. 6
- It may state two separate claims as one. 18
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our best model, DiT-XL/2, is compute-efficient and outperforms all prior U-Net-based diffusion models, like ADM and LDM.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Cross-attention adds the most Gflops to the model, roughly a 15% overhead.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“As with prior work using guidance, we observe that larger scales increase visual fidelity and decrease sample diversity.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For both the 256 × 256 and 512 × 512 DiT-XL/2 models, we never observed FID saturate and continued training them as long as possible.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Of the three block designs we explore, adaLN adds the least Gflops and is thus the most compute-efficient.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our best model, DiT-XL/2, is compute-efficient and outperforms all prior U-Net-based diffusion models, like ADM and LDM.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Table 2. Benchmarking class-conditional image generation on ImageNet 256×256. DiT-XL/2 achieves state-of-the-art FID.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. The quote only partly states this claim.
- Rests on an assumption: FID-50K values reported by prior work are directly comparable to the FID-50K values computed in this paper.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When trained for only 2.35M steps (similar to ADM), XL/2 still outperforms all prior diffusion models with an FID of 2.55.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In all cases, we find that increasing model size and decreasing patch size yields considerably improved diffusion models.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“XL/2 again outperforms all prior diffusion models at this resolution, improving the previous best FID of 3.85 achieved by ADM to 3.04.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: FID-50K values reported by prior work are directly comparable to the FID-50K values computed in this paper.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we did not find learning rate warmup nor regularization necessary to train DiTs to high performance.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing the Gflops in the model—either by increasing transformer depth/width or increasing the number of input tokens—yields significant improvements in visual fidelity.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In all cases, we find that increasing model size and decreasing patch size yields considerably improved diffusion models.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We find a strong negative correlation between model Gflops and FID-50K, suggesting that additional model compute is the critical ingredient for improved DiT models.”
- Also stated in: § 100 101 102 · boosted
“Transformer Gflops are strongly correlated with FID.”
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 100 101 102 · boosted
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Finally, we also observe that DiT-XL/2 achieves higher recall values at all tested classifier-free guidance scales compared to LDM-4 and LDM-8.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Increasing DiT model Gflops (via transformer size or number of input tokens) causes the training loss to decrease more rapidly and saturate at a lower value.”
- Also stated in: § 0 10K 20K 30K 40K 50K 60K 70K 80K 90K 100K · plain
“Note that scaled-up DiT models exhibit lower training losses.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 0 10K 20K 30K 40K 50K 60K 70K 80K 90K 100K · plain
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“We did not tune learning rates, decay/warm-up schedules, Adam β1/β2 or weight decays.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“which have been shown to scale more effectively for visual recognition than traditional convolutional networks (e.g., ResNet [15]).”
What the sources say
- Not matchedcites [10] Dosovitskiy, An image is worth 16x16 words: Transformers for image recognition at scale
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Not matched
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Even without these techniques, training was highly stable across all model configs and we did not observe any loss spikes commonly seen when training transformers.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“diffusion models have been at the forefront of recent advances in image-level generative models [9,46]; yet, they all adopt a convolutional U-Net architecture as the de-facto choice of backbone.”
What the sources say
- Not matchedcites [9] Dhariwal, Diffusion models beat gans on image synthesis
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [46] Ramesh, 2022, Hierarchical text-conditional image generation with clip latents
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
In the paper
“Note that prior work [9] measures Precision and Recall using 1000 real samples for 512 × 512 resolution; for consistency, we do the same.”
§ 107 108 109 1010 1011 1012 > 5.1. State-of-the-Art Diffusion Models
What the sources say
- Not matchedcites [9] Dhariwal, Diffusion models beat gans on image synthesis
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainn = 1,000- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“halving pwill quadruple T , and thus at least quadruple total transformer Gflops.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A smaller patch size p results in a longer sequence length and thus more Gflops.”
§ 3. Diffusion Transformers > 3.2. Diffusion Transformer Design Space
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper relies on this without support.
FID-50K values reported by prior work are directly comparable to the FID-50K values computed in this paper.
“We show samples from the model in Figures 1, and we compare against state-of-the-art class-conditional generative models. We report results in Table 2.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Unlike prior works that employ text-to-image (T2I) U-Net [10, 33, 35, 40] for talking head generation, MoCha is built on a diffusion transformer (DiT) [26]. By incorporating text and speech conditions sequentially via cross-attention, it effectively captures both semantics and temporal dynamics.”
From MoCha: Towards Movie-Grade Talking Character Synthesis (2025) · cites this paper as [26]
In the citing paper
“Supervised learning, a foundational approach in AI, uses labeled datasets to guide models towards accurate predictions, and it has been integral to various applications, including image recognition and NLP [163], [164], [165].”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [164]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930
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
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Research works printed but not linked: 3
- Chen, Generative pre-training from pixels
- Dosovitskiy, An image is worth 16x16 words: Transformers for image recognition at scale
- Goodfellow, Generative adversarial nets
Cited by
Sorted by citations
FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent SpacePreprint
Labs, B. F., Batifol, S., Blattmann, A., Boesel, F., Consul, S., Diagne, C., Dockhorn, T., English, J., English, Z., Esser, P., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.15742 · Cited by 1,030
Diffusion models in medical imaging: A comprehensive survey
Kazerouni, A., Aghdam, E. K., Heidari, M., Azad, R., Fayyaz, M., Hacihaliloglu, I., & Merhof, D. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102846 · Cited by 1,006
Emu3: Next-Token Prediction is All You NeedPreprint
Wang, X., Zhang, X., Luo, Z., Sun, Q., Cui, Y., Wang, J., Zhang, F., Wang, Y., Li, Z., Yu, Q., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.18869 · Cited by 889
Structured 3D Latents for Scalable and Versatile 3D Generation
Xiang, J., Lv, Z., Xu, S., Yu, D., Wang, R., Zhang, B., Chen, D., Tong, X., & Yang, J. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02000 · Cited by 633
Adversarial Diffusion Distillation
Sauer, A., Lorenz, D., Blattmann, A., & Rombach, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73016-0_6 · Cited by 617
LRM: Large Reconstruction Model for Single Image to 3DPreprint
Hong, Y., Zhang, K., Gu, J., Bi, S., Zhou, Y. M., Liu, D., Liu, F., Sunkavalli, K., Bui, T., & Tan, H. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.04400 · Cited by 510
SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., Müller, J., Penna, J., & Rombach, R. (2023) · arXiv · doi:10.48550/arxiv.2307.01952 · Cited by 455
Language Model Beats Diffusion -- Tokenizer is Key to Visual GenerationPreprint
Yu, L., Lezama, J., Gundavarapu, N. B., Versari, L., Sohn, K., Minnen, D. C., Cheng, Y., Birodkar, V., Gupta, A., Gu, X., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.05737 · Cited by 439
LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models
Wang, Y., Chen, X., Ma, X., Zhou, S., Huang, Z., Yang, C., Yang, C., He, Y., Yu, J., Yang, P., et al. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02295-1 · Cited by 436
Foundation Models for Time Series Analysis: A Tutorial and Survey
Liang, Y., Wen, H., Nie, Y., Jiang, Y., Jin, M., Song, D., Pan, S., & Wen, Q. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671451 · Cited by 368
SiT: Exploring Flow and Diffusion-Based Generative Models with Scalable Interpolant Transformers
Ma, N., Goldstein, M., Albergo, M. S., Boffi, N. M., Vanden-Eijnden, E., & Xie, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72980-5_2 · Cited by 364
Self-citationHumans in 4D: Reconstructing and Tracking Humans with Transformers
Goel, S., Pavlakos, G., Rajasegaran, J., Kanazawa, A., & Malik, J. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01358 · Cited by 339
VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic FaithfulnessPreprint
Zheng, D., Huang, Z., Liu, H., Zou, K., He, Y., Zhang, F., Gu, L., Zhang, Y., He, J., Zheng, W., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.21755 · Cited by 321
PIXART-$$\Sigma $$: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
Chen, J., Ge, C., Xie, E., Wu, Y., Yao, L., Ren, X., Wang, Z., Luo, P., Lu, H., & Li, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73411-3_5 · Cited by 312
SVDiff: Compact Parameter Space for Diffusion Fine-Tuning
Han, L., Li, Y., Zhang, H., Milanfar, P., Metaxas, D., & Yang, F. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00673 · Cited by 302
Text-to-3D using Gaussian Splatting
Chen, Z., Wang, F., Wang, Y., & Liu, H. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02022 · Cited by 302
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion TransformersPreprint
Xie, E., Chen, J. S., Chen, J., Cai, H., Tang, H., Lin, Y., Zhang, Z., Li, M., Zhu, L., Lu, Y., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.10629 · Cited by 282
SkyReels-V2: Infinite-length Film Generative ModelPreprint
Chen, G., Lin, D., Yang, J., Lin, C., Zhu, J., Fan, M., Zhang, H., Chen, S., Chen, Z., Ma, C., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.13074 · Cited by 265
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Grauman, K. L., Westbury, A., Torresani, L., Kitani, K., Malik, J., Afouras, T., Ashutosh, K., Baiyya, V. B., Bansal, S., Boote, B., et al. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01834 · Cited by 267
Photorealistic Video Generation with Diffusion Models
Gupta, A., Yu, L., Sohn, K., Gu, X., Hahn, M., Fei-Fei, L., Essa, I. A., Jiang, L., & Lezama, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72986-7_23 · Cited by 253
The Stable Signature: Rooting Watermarks in Latent Diffusion Models
Fernandez, P., Couairon, G., Jégou, H., Douze, M., & Furon, T. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02053 · Cited by 251
Transformers without Normalization
Zhu, J., Chen, X., He, K., LeCun, Y., & Liu, Z. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01388 · Cited by 247
Resource-efficient Algorithms and Systems of Foundation Models: A Survey
Xu, M., Cai, D., Yin, W., Wang, S., Jin, X., & Liu, X. (2024) · ACM Computing Surveys · doi:10.1145/3706418 · Cited by 255
Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
Zhu, C., Yu, R., Feng, S., Burchfiel, B., Shah, P., & Gupta, A. (2025) · Robotics: Science and Systems · doi:10.15607/rss.2025.xxi.015 · Cited by 240
Show-o2: Improved Native Unified Multimodal Models
Xie, J., Yang, Z., & Shou, M. Z. (2025) · neural information processing systems · doi:10.52202/085713-1584 · Cited by 236
Zou, Z., Yu, Z., Guo, Y., Li, Y., Ding, L., Cao, Y., & Zhang, S. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00983 · Cited by 234
Your Diffusion Model is Secretly a Zero-Shot Classifier
Li, A. C., Prabhudesai, M., Duggal, S., Brown, E. V., & Pathak, D. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00210 · Cited by 242
Evans, Z., Parker, J. D., Carr, C., Zukowski, Z., Taylor, J., & Pons, J. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888461 · Cited by 236
Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction ModelPreprint
Li, J., Tan, H., Zhang, K., Xu, Z., Luan, F., Xu, Y., Hong, Y., Sunkavalli, K., Shakhnarovich, G., & Bi, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.06214 · Cited by 229
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
Li, Z., Cao, M., Wang, X., Qi, Z., Cheng, M., & Shan, Y. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00825 · Cited by 233
A Survey on Video Diffusion Models
Xing, Z., Feng, Q., Chen, H., Dai, Q., Hu, H., Xu, H., Wu, Z., & Jiang, Y. (2024) · ACM Computing Surveys · doi:10.1145/3696415 · Cited by 228
Lumiere: A Space-Time Diffusion Model for Video Generation
Bar-Tal, O., Chefer, H., Tov, O., Herrmann, C., Paiss, R., Zada, S., Ephrat, A., Hur, J., Liu, G., Raj, A., et al. (2024) · SIGGRAPH Asia Conference Papers · doi:10.1145/3680528.3687614 · Cited by 215
Sapiens: Foundation for Human Vision Models
Khirodkar, R., Bagautdinov, T., Martinez, J., Zhaoen, S., James, A., Selednik, P., Anderson, S., & Saito, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73235-5_12 · Cited by 213
Q-Diffusion: Quantizing Diffusion Models
Li, X., Liu, Y., Lian, L., Yang, H., Dong, Z., Kang, D. D., Zhang, S., & Keutzer, K. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01608 · Cited by 215
Tian, L., Wang, Q. J., Zhang, B., & Bo, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73010-8_15 · Cited by 211
Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
Sauer, A., Boesel, F., Dockhorn, T., Blattmann, A., Esser, P., & Rombach, R. (2024) · SIGGRAPH Asia Conference Papers · doi:10.1145/3680528.3687625 · Cited by 217
Recammaster: Camera-Controlled Generative Rendering From a Single Video
Bai, J., Xia, M., Fu, X., Wang, X., Mu, L., Cao, J., Liu, Z., Hu, H., Bai, X., Wan, P., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01376 · Cited by 199
State of the Art on Diffusion Models for Visual Computing
Po, R., Yifan, W., Golyanik, V., Aberman, K., Barron, J. T., Bermano, A. H., Chan, E. R., Dekel, T., Holynski, A., Kanazawa, A., et al. (2024) · Computer Graphics Forum · doi:10.1111/cgf.15063 · Cited by 198
CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model
Wang, Z., Wang, Y., Chen, Y., Xiang, C., Chen, S., Yu, D., Li, C., Su, H., & Zhu, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72751-1_4 · Cited by 189
Flow Matching in Latent SpacePreprint
Dao, Q. T., Phung, H., Nguyen, B., & Tran, A. T. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.08698 · Cited by 186
Efficient Diffusion Training via Min-SNR Weighting Strategy
Hang, T., Gu, S., Li, C., Bao, J., Chen, D., Hu, H., Geng, X., & Guo, B. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00684 · Cited by 188
Raising the Bar of AI-generated Image Detection with CLIP
Cozzolino, D., Poggi, G., Corvi, R., Nießner, M., & Verdoliva, L. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00439 · Cited by 181
Analyzing and Improving the Training Dynamics of Diffusion Models
Karras, T., Aittala, M., Lehtinen, J., Hellsten, J., Aila, T., & Laine, S. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02282 · Cited by 186
Chen, P., Shen, M., Ye, P. D., Cao, J., Tu, C., Bouganis, C.-S., Zhao, Y., & Chen, T. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02871-7 · Cited by 178
Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Models
Luo, Z., Gustafsson, F., Zhao, Z., Sjölund, J., & Schön, T. B. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00169 · Cited by 175
ResDiff: Combining CNN and Diffusion Model for Image Super-resolution
Shang, S., Shan, Z., Liu, G., Wang, L., Wang, X., Zhang, Z., & Zhang, J. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i8.28746 · Cited by 167
Protenix - Advancing Structure Prediction Through a Comprehensive AlphaFold3 ReproductionPreprint
ByteDance AML AI4Science Team, Chen, X., Zhang, Y., Lu, C., Ma, W., Guan, J., Gong, C., Yang, J., Zhang, H., Zhang, K., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.01.08.631967 · Cited by 167
EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions
Chen, Z., Cao, J., Chen, Z., Li, Y., & Ma, C. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i3.32241 · Cited by 173
A Survey on Diffusion Models for Time Series and Spatio-Temporal Data
Yang, Y., Jin, M., Wen, H., Zhang, C., Liang, Y., Ma, L., Wang, Y., Liu, C., Yang, B., Xu, Z., et al. (2025) · ACM Computing Surveys · doi:10.1145/3783986 · Cited by 166
ZigMa: A DiT-style Zigzag Mamba Diffusion Model
Hu, V. T., Baumann, S. A., Gui, M., Grebenkova, O., Ma, P., Fischer, J., & Ommer, B. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72664-4_9 · Cited by 159
On the design fundamentals of diffusion models: A survey
Chang, Z., Koulieris, G. A., Chang, H. J., & Shum, H. P. H. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111934 · Cited by 158
Atom-level enzyme active site scaffolding using RFdiffusion2
Ahern, W., Yim, J., Tischer, D., Salike, S., Woodbury, S. M., Kim, D., Kalvet, I., Kipnis, Y., Coventry, B., Altae-Tran, H., et al. (2025) · Nature Methods · doi:10.1038/s41592-025-02975-x · Cited by 157
Intriguing properties of synthetic images: from generative adversarial networks to diffusion models
Corvi, R., Cozzolino, D., Poggi, G., Nagano, K., & Verdoliva, L. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00104 · Cited by 142
REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
Leng, X., Singh, J., Hou, Y., Xing, Z., Xie, S., & Zheng, L. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01697 · Cited by 142
Self-citationScaling Rectified Flow Transformers for High-Resolution Image Synthesis
Esser, P., Kulal, S., Blattmann, A., Entezari, R., Müller, J., Saini, H., Levi, Y., Lorenz, D., Sauer, A., Boesel, F., et al. (2024) · arXiv · doi:10.48550/arxiv.2403.03206 · Cited by 140
Timestep Embedding Tells: It’s Time to Cache for Video Diffusion Model
Liu, F., Zhang, S., Wang, X., Wei, Y., Qiu, H., Zhao, Y., Zhang, Y., Ye, Q., & Wan, F. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00689 · Cited by 139
LongCat-Image Technical ReportPreprint
Meituan LongCat Team, Ma, H., Tan, H., Huang, J., Wu, J., He, J.-Y., Gao, L., Xiao, S., Wei, X., Ma, X., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.07584 · Cited by 135
Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
Kawaharazuka, K., Oh, J., Yamada, J., Posner, I., & Zhu, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3609980 · Cited by 135
A careful examination of large behavior models for multitask dexterous manipulation
Barreiros, J. A. L., Beaulieu, A., Bhat, A. D., Cory, R., Cousineau, E. A., Dai, H., Fang, C.-H., Hashimoto, K., Irshad, M. Z., Itkina, M., et al. (2026) · Science Robotics · doi:10.1126/scirobotics.aea6201 · Cited by 137
ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold LearningPreprint
Yang, Y., Zeng, S., Lin, T., Chang, X., Qi, D., Xiao, J., Liu, H., Chen, R., Chen, Y., Huo, D., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.11236 · Cited by 133
Scalable Adaptive Computation for Iterative GenerationPreprint
Jabri, A., Fleet, D. J., & Chen, T. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.11972 · Cited by 132
A Reparameterized Discrete Diffusion Model for Text GenerationPreprint
Lin, Z., Yuan, J., Yu, L., & Kong, L. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.05737 · Cited by 124
From Large Language Models to Large Multimodal Models: A Literature Review
Huang, D., Yan, C., Li, Q., & Peng, X. (2024) · Applied Sciences · doi:10.3390/app14125068 · Cited by 125
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
Lin, G., Jiang, J., Yang, J., Zheng, Z., Liang, C., Zhang, Y., & Liu, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01285 · Cited by 121
Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
Wu, S., Huang, M., Wu, W. Y., Cheng, Y., Ding, F., & He, Q. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01736 · Cited by 123
TRACT: Denoising Diffusion Models with Transitive Closure Time-DistillationPreprint
Berthelot, D., Autef, A., Lin, J., Yap, D. A., Zhai, S., Hu, S., Zheng, D., Talbott, W. A., & Gu, E. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.04248 · Cited by 120
Gat, I., Remez, T., Shaul, N., Kreuk, F., Chen, R. T. Q., Synnaeve, G., Adi, Y., & Lipman, Y. (2024) · neural information processing systems · doi:10.52202/079017-4239 · Cited by 119
DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction ModelPreprint
Xu, Y., Tan, H., Luan, F., Bi, S., Wang, P., Li, J., Shi, Z., Sunkavalli, K., Wetzstein, G., Xu, Z., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.09217 · Cited by 119
Ma, Y., Liu, X., Chen, X., Liu, W., Wu, C., Wu, Z., Pan, Z., Xie, Z., Zhang, H., Yu, X., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00725 · Cited by 118
Xie, E., Chen, J., Zhao, Y., Yu, J., Zhu, L., Wu, C., Lin, Y., Zhang, Z., Li, M., Chen, J., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.18427 · Cited by 118
Improving Sample Quality of Diffusion Models Using Self-Attention Guidance
Hong, S., Lee, G., Jang, W., & Kim, S. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00686 · Cited by 120
Comprehensive exploration of diffusion models in image generation: a survey
Chen, H., Xiang, Q., Hu, J., Ye, M., Yu, C., Cheng, H., & Zhang, L. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11110-3 · Cited by 115
TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models
Yu, M., Hu, W., Xing, J., & Shan, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00017 · Cited by 115
Controllable Generation With Text-to-Image Diffusion Models: A Survey
Cao, P., Zhou, F., Song, Q., & Yang, L. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3646548 · Cited by 113
Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
Gu, Z., Yan, R., Lu, J., Li, P., Dou, Z., Si, C., Dong, Z., Liu, Q., Lin, C. C., Liu, Z., et al. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730607 · Cited by 113
Qian, Q., Luo, J. T., & Qin, Y. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3408058 · Cited by 112
Fast Training of Diffusion Models with Masked TransformersPreprint
Zheng, H., Nie, W., Vahdat, A., & Anandkumar, A. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.09305 · Cited by 111
Gong, H., Kang, L., Wang, Y., Wang, Y., Wan, X., Wu, X., & Li, H. (2025) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi60581.2025.10980694 · Cited by 110
IRASim: A Fine-Grained World Model for Robot Manipulation
Zhu, F., Wu, H., Guo, S., Liu, Y., Cheang, C., & Kong, T. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00917 · Cited by 110
Federated Recommender System Based on Diffusion Augmentation and Guided Denoising
Di, Y., Shi, H., Wang, X., Ma, R., & Liu, Y. (2024) · ACM Transactions on Information Systems · doi:10.1145/3688570 · Cited by 107
Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval
Yu, J., Bai, J., Qin, Y., Liu, Q., Wang, X., Wan, P., Zhang, D., & Liu, X. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763833 · Cited by 107
Editing Implicit Assumptions in Text-to-Image Diffusion Models
Orgad, H., Kawar, B., & Belinkov, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00649 · Cited by 105
TrafficFormer: An Efficient Pre-trained Model for Traffic Data
Zhou, G., Guo, X., Liu, Z., Li, T., Li, Q., & Xu, K. (2025) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp61157.2025.00102 · Cited by 104
McIntosh, T. R., Susnjak, T., Liu, T., Watters, P., Xu, D., Liu, D., & Halgamuge, M. N. (2025) · Technologies · doi:10.3390/technologies13020051 · Cited by 102
“Generative AI model architectures have seen significant developments, with four key domains standing out: • Transformer Models: Transformer models have signifi-cantly revolutionized the field of AI, especially in NLP, due to their higher efficiency and scalability [139], [140], [141].”
BackgroundEasyControl: Adding Efficient and Flexible Control for Diffusion Transformer
Zhang, Y. S., Yuan, Y., Song, Y., Wang, H., & Liu, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01814 · Cited by 101
Randomized Autoregressive Visual Generation
Yu, Q., He, J., Deng, X., Shen, X., & Chen, L.-C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01713 · Cited by 100
DiffiT: Diffusion Vision Transformers for Image Generation
Hatamizadeh, A., Song, J., Liu, G., Kautz, J., & Vahdat, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73242-3_3 · Cited by 102
Track2Act: Predicting Point Tracks from Internet Videos Enables Generalizable Robot Manipulation
Bharadhwaj, H., Mottaghi, R., Gupta, A., & Tulsiani, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73116-7_18 · Cited by 98
MTGR: Industrial-Scale Generative Recommendation Framework in Meituan
Han, R., Yin, B., Chen, S., Jiang, H., Jiang, F., Li, X., Ma, C., Huang, M., Li, X., Jing, C., et al. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761565 · Cited by 97
Alimisis, P., Mademlis, I., Grammatikis, P. I. R., Sarigiannidis, P. G., & Papadopoulos, G. T. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11116-x · Cited by 96
Xie, E., Yao, L., Shi, H., Liu, Z., Zhou, D., Liu, Z., Li, J., & Li, Z. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00390 · Cited by 97
Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment
Liu, L., Ma, T., Li, B., Chen, Z., Liu, J., Li, G., Zhou, S., He, Q., & Wu, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01387 · Cited by 96
Efficient Diffusion Models for Vision: A SurveyPreprint
Ulhaq, A., & Akhtar, N. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.09292 · Cited by 96
Harnessing large vision and language models in agriculture: a review
Zhu, H., Qin, S., Su, M., Lin, C., Li, A., & Gao, J. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1579355 · Cited by 97
MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices
Zhao, Y., Xu, Y., Xiao, Z., Jia, H., & Hou, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73033-7_13 · Cited by 94
Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation
Kingma, D. P., & Gao, R. (2023) · neural information processing systems · doi:10.52202/075280-2858 · Cited by 103
He, Z., Wang, Y.-H., & Zhang, J. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102654 · Cited by 91
Tian, L., Wang, Q., Zhang, B., & Bo, L. (2024) · arXiv · doi:10.48550/arxiv.2402.17485 · Cited by 92
Masked Diffusion Transformer is a Strong Image Synthesizer
Gao, S., Zhou, P., Cheng, M.-M., & Yan, S. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02117 · Cited by 91
Online Detection of AI-Generated Images
Epstein, D. C., Jain, I., Wang, O., & Zhang, R. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00045 · Cited by 91
Metadata
- Authors
- Peebles, W., & Xie, S.
- Affiliations
- University of California, Berkeley (US)
- New York University (US)
- ORCID
- Xie, Saining
- Venue
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 4172-4182
- OpenAlex
- W4390872297
- Semantic Scholar
- 736973165f98105fec3729b7db414ae4d80fcbeb
- Cited by
- 2,284
- References
- 59
- Citations by year
- 2026: 1007 · 2025: 925 · 2024: 315 · 2023: 37
- FWCI
- 244.26
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- diffusion models, latent diffusion models, diffusion transformer, scalability, image generation
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.
A language model drew the claims from the paper on 2026-11-08, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-08 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
