Merge branch 'main' into integrations/wan-vace

Author: linoytsaban

docs/source/en/_toctree.yml

@@ -17,8 +17,6 @@
     title: AutoPipeline
   - local: tutorials/basic_training
     title: Train a diffusion model
-  - local: tutorials/fast_diffusion
-    title: Accelerate inference of text-to-image diffusion models
   title: Tutorials
 - sections:
   - local: using-diffusers/loading

docs/source/en/api/models/asymmetricautoencoderkl.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AsymmetricAutoencoderKL
 
-Improved larger variational autoencoder (VAE) model with KL loss for inpainting task: [Designing a Better Asymmetric VQGAN for StableDiffusion](https://arxiv.org/abs/2306.04632) by Zixin Zhu, Xuelu Feng, Dongdong Chen, Jianmin Bao, Le Wang, Yinpeng Chen, Lu Yuan, Gang Hua.
+Improved larger variational autoencoder (VAE) model with KL loss for inpainting task: [Designing a Better Asymmetric VQGAN for StableDiffusion](https://huggingface.co/papers/2306.04632) by Zixin Zhu, Xuelu Feng, Dongdong Chen, Jianmin Bao, Le Wang, Yinpeng Chen, Lu Yuan, Gang Hua.
 
 The abstract from the paper is:
 

docs/source/en/api/models/autoencoderkl.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AutoencoderKL
 
-The variational autoencoder (VAE) model with KL loss was introduced in [Auto-Encoding Variational Bayes](https://arxiv.org/abs/1312.6114v11) by Diederik P. Kingma and Max Welling. The model is used in 🤗 Diffusers to encode images into latents and to decode latent representations into images.
+The variational autoencoder (VAE) model with KL loss was introduced in [Auto-Encoding Variational Bayes](https://huggingface.co/papers/1312.6114v11) by Diederik P. Kingma and Max Welling. The model is used in 🤗 Diffusers to encode images into latents and to decode latent representations into images.
 
 The abstract from the paper is:
 

docs/source/en/api/models/consisid_transformer3d.md

@@ -11,7 +11,7 @@ specific language governing permissions and limitations under the License. -->
 
 # ConsisIDTransformer3DModel
 
-A Diffusion Transformer model for 3D data from [ConsisID](https://github.com/PKU-YuanGroup/ConsisID) was introduced in [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://arxiv.org/pdf/2411.17440) by Peking University & University of Rochester & etc.
+A Diffusion Transformer model for 3D data from [ConsisID](https://github.com/PKU-YuanGroup/ConsisID) was introduced in [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://huggingface.co/papers/2411.17440) by Peking University & University of Rochester & etc.
 
 The model can be loaded with the following code snippet.
 

docs/source/en/api/models/controlnet_hunyuandit.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # HunyuanDiT2DControlNetModel
 
-HunyuanDiT2DControlNetModel is an implementation of ControlNet for [Hunyuan-DiT](https://arxiv.org/abs/2405.08748).
+HunyuanDiT2DControlNetModel is an implementation of ControlNet for [Hunyuan-DiT](https://huggingface.co/papers/2405.08748).
 
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
 

docs/source/en/api/models/controlnet_sparsectrl.md

@@ -11,11 +11,11 @@ specific language governing permissions and limitations under the License. -->
 
 # SparseControlNetModel
 
-SparseControlNetModel is an implementation of ControlNet for [AnimateDiff](https://arxiv.org/abs/2307.04725).
+SparseControlNetModel is an implementation of ControlNet for [AnimateDiff](https://huggingface.co/papers/2307.04725).
 
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
 
-The SparseCtrl version of ControlNet was introduced in [SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://arxiv.org/abs/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
+The SparseCtrl version of ControlNet was introduced in [SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://huggingface.co/papers/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
 
 The abstract from the paper is:
 

docs/source/en/api/pipelines/amused.md

@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.
 
 aMUSEd was introduced in [aMUSEd: An Open MUSE Reproduction](https://huggingface.co/papers/2401.01808) by Suraj Patil, William Berman, Robin Rombach, and Patrick von Platen.
 
-Amused is a lightweight text to image model based off of the [MUSE](https://arxiv.org/abs/2301.00704) architecture. Amused is particularly useful in applications that require a lightweight and fast model such as generating many images quickly at once.
+Amused is a lightweight text to image model based off of the [MUSE](https://huggingface.co/papers/2301.00704) architecture. Amused is particularly useful in applications that require a lightweight and fast model such as generating many images quickly at once.
 
 Amused is a vqvae token based transformer that can generate an image in fewer forward passes than many diffusion models. In contrast with muse, it uses the smaller text encoder CLIP-L/14 instead of t5-xxl. Due to its small parameter count and few forward pass generation process, amused can generate many images quickly. This benefit is seen particularly at larger batch sizes.
 

docs/source/en/api/pipelines/animatediff.md

@@ -18,7 +18,7 @@ specific language governing permissions and limitations under the License.
 
 ## Overview
 
-[AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://arxiv.org/abs/2307.04725) by Yuwei Guo, Ceyuan Yang, Anyi Rao, Yaohui Wang, Yu Qiao, Dahua Lin, Bo Dai.
+[AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://huggingface.co/papers/2307.04725) by Yuwei Guo, Ceyuan Yang, Anyi Rao, Yaohui Wang, Yu Qiao, Dahua Lin, Bo Dai.
 
 The abstract of the paper is the following:
 
@@ -187,7 +187,7 @@ Here are some sample outputs:
 
 ### AnimateDiffSparseControlNetPipeline
 
-[SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://arxiv.org/abs/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
+[SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://huggingface.co/papers/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
 
 The abstract from the paper is:
 
@@ -751,7 +751,7 @@ export_to_gif(frames, "animation.gif")
 
 ## Using FreeInit
 
-[FreeInit: Bridging Initialization Gap in Video Diffusion Models](https://arxiv.org/abs/2312.07537) by Tianxing Wu, Chenyang Si, Yuming Jiang, Ziqi Huang, Ziwei Liu.
+[FreeInit: Bridging Initialization Gap in Video Diffusion Models](https://huggingface.co/papers/2312.07537) by Tianxing Wu, Chenyang Si, Yuming Jiang, Ziqi Huang, Ziwei Liu.
 
 FreeInit is an effective method that improves temporal consistency and overall quality of videos generated using video-diffusion-models without any addition training. It can be applied to AnimateDiff, ModelScope, VideoCrafter and various other video generation models seamlessly at inference time, and works by iteratively refining the latent-initialization noise. More details can be found it the paper.
 
@@ -920,7 +920,7 @@ export_to_gif(frames, "animatelcm-motion-lora.gif")
 
 ## Using FreeNoise
 
-[FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://arxiv.org/abs/2310.15169) by Haonan Qiu, Menghan Xia, Yong Zhang, Yingqing He, Xintao Wang, Ying Shan, Ziwei Liu.
+[FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://huggingface.co/papers/2310.15169) by Haonan Qiu, Menghan Xia, Yong Zhang, Yingqing He, Xintao Wang, Ying Shan, Ziwei Liu.
 
 FreeNoise is a sampling mechanism that can generate longer videos with short-video generation models by employing noise-rescheduling, temporal attention over sliding windows, and weighted averaging of latent frames. It also can be used with multiple prompts to allow for interpolated video generations. More details are available in the paper.
 

docs/source/en/api/pipelines/audioldm2.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AudioLDM 2
 
-AudioLDM 2 was proposed in [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://arxiv.org/abs/2308.05734) by Haohe Liu et al. AudioLDM 2 takes a text prompt as input and predicts the corresponding audio. It can generate text-conditional sound effects, human speech and music.
+AudioLDM 2 was proposed in [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://huggingface.co/papers/2308.05734) by Haohe Liu et al. AudioLDM 2 takes a text prompt as input and predicts the corresponding audio. It can generate text-conditional sound effects, human speech and music.
 
 Inspired by [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/overview), AudioLDM 2 is a text-to-audio _latent diffusion model (LDM)_ that learns continuous audio representations from text embeddings. Two text encoder models are used to compute the text embeddings from a prompt input: the text-branch of [CLAP](https://huggingface.co/docs/transformers/main/en/model_doc/clap) and the encoder of [Flan-T5](https://huggingface.co/docs/transformers/main/en/model_doc/flan-t5). These text embeddings are then projected to a shared embedding space by an [AudioLDM2ProjectionModel](https://huggingface.co/docs/diffusers/main/api/pipelines/audioldm2#diffusers.AudioLDM2ProjectionModel). A [GPT2](https://huggingface.co/docs/transformers/main/en/model_doc/gpt2) _language model (LM)_ is used to auto-regressively predict eight new embedding vectors, conditional on the projected CLAP and Flan-T5 embeddings. The generated embedding vectors and Flan-T5 text embeddings are used as cross-attention conditioning in the LDM. The [UNet](https://huggingface.co/docs/diffusers/main/en/api/pipelines/audioldm2#diffusers.AudioLDM2UNet2DConditionModel) of AudioLDM 2 is unique in the sense that it takes **two** cross-attention embeddings, as opposed to one cross-attention conditioning, as in most other LDMs.
 

docs/source/en/api/pipelines/blip_diffusion.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # BLIP-Diffusion
 
-BLIP-Diffusion was proposed in [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://arxiv.org/abs/2305.14720). It enables zero-shot subject-driven generation and control-guided zero-shot generation.
+BLIP-Diffusion was proposed in [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://huggingface.co/papers/2305.14720). It enables zero-shot subject-driven generation and control-guided zero-shot generation.
 
 
 The abstract from the paper is:

docs/source/en/api/pipelines/cogvideox.md

@@ -19,7 +19,7 @@
   <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
 </div>
 
-[CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://arxiv.org/abs/2408.06072) from Tsinghua University & ZhipuAI, by Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, Da Yin, Xiaotao Gu, Yuxuan Zhang, Weihan Wang, Yean Cheng, Ting Liu, Bin Xu, Yuxiao Dong, Jie Tang.
+[CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://huggingface.co/papers/2408.06072) from Tsinghua University & ZhipuAI, by Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, Da Yin, Xiaotao Gu, Yuxuan Zhang, Weihan Wang, Yean Cheng, Ting Liu, Bin Xu, Yuxiao Dong, Jie Tang.
 
 The abstract from the paper is:
 

docs/source/en/api/pipelines/consisid.md

@@ -19,7 +19,7 @@
   <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
 </div>
 
-[Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://arxiv.org/abs/2411.17440) from Peking University & University of Rochester & etc, by Shenghai Yuan, Jinfa Huang, Xianyi He, Yunyang Ge, Yujun Shi, Liuhan Chen, Jiebo Luo, Li Yuan.
+[Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://huggingface.co/papers/2411.17440) from Peking University & University of Rochester & etc, by Shenghai Yuan, Jinfa Huang, Xianyi He, Yunyang Ge, Yujun Shi, Liuhan Chen, Jiebo Luo, Li Yuan.
 
 The abstract from the paper is:
 

docs/source/en/api/pipelines/controlnet_hunyuandit.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet with Hunyuan-DiT
 
-HunyuanDiTControlNetPipeline is an implementation of ControlNet for [Hunyuan-DiT](https://arxiv.org/abs/2405.08748).
+HunyuanDiTControlNetPipeline is an implementation of ControlNet for [Hunyuan-DiT](https://huggingface.co/papers/2405.08748).
 
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
 

docs/source/en/api/pipelines/framepack.md

@@ -18,7 +18,7 @@
   <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
 </div>
 
-[Packing Input Frame Context in Next-Frame Prediction Models for Video Generation](https://arxiv.org/abs/2504.12626) by Lvmin Zhang and Maneesh Agrawala.
+[Packing Input Frame Context in Next-Frame Prediction Models for Video Generation](https://huggingface.co/papers/2504.12626) by Lvmin Zhang and Maneesh Agrawala.
 
 *We present a neural network structure, FramePack, to train next-frame (or next-frame-section) prediction models for video generation. The FramePack compresses input frames to make the transformer context length a fixed number regardless of the video length. As a result, we are able to process a large number of frames using video diffusion with computation bottleneck similar to image diffusion. This also makes the training video batch sizes significantly higher (batch sizes become comparable to image diffusion training). We also propose an anti-drifting sampling method that generates frames in inverted temporal order with early-established endpoints to avoid exposure bias (error accumulation over iterations). Finally, we show that existing video diffusion models can be finetuned with FramePack, and their visual quality may be improved because the next-frame prediction supports more balanced diffusion schedulers with less extreme flow shift timesteps.*
 

docs/source/en/api/pipelines/hunyuandit.md

@@ -13,7 +13,7 @@ specific language governing permissions and limitations under the License.
 # Hunyuan-DiT
 ![chinese elements understanding](https://github.com/gnobitab/diffusers-hunyuan/assets/1157982/39b99036-c3cb-4f16-bb1a-40ec25eda573)
 
-[Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding](https://arxiv.org/abs/2405.08748) from Tencent Hunyuan.
+[Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding](https://huggingface.co/papers/2405.08748) from Tencent Hunyuan.
 
 The abstract from the paper is:
 

docs/source/en/api/pipelines/i2vgenxl.md

@@ -47,7 +47,7 @@ Sample output with I2VGenXL:
 * Unlike SVD, it additionally accepts text prompts as inputs.
 * It can generate higher resolution videos.
 * When using the [`DDIMScheduler`] (which is default for this pipeline), less than 50 steps for inference leads to bad results.
-* This implementation is 1-stage variant of I2VGenXL. The main figure in the [I2VGen-XL](https://arxiv.org/abs/2311.04145) paper shows a 2-stage variant, however, 1-stage variant works well. See [this discussion](https://github.com/huggingface/diffusers/discussions/7952) for more details.
+* This implementation is 1-stage variant of I2VGenXL. The main figure in the [I2VGen-XL](https://huggingface.co/papers/2311.04145) paper shows a 2-stage variant, however, 1-stage variant works well. See [this discussion](https://github.com/huggingface/diffusers/discussions/7952) for more details.
 
 ## I2VGenXLPipeline
 [[autodoc]] I2VGenXLPipeline

docs/source/en/api/pipelines/latte.md

@@ -16,13 +16,13 @@
 
 ![latte text-to-video](https://github.com/Vchitect/Latte/blob/52bc0029899babbd6e9250384c83d8ed2670ff7a/visuals/latte.gif?raw=true)
 
-[Latte: Latent Diffusion Transformer for Video Generation](https://arxiv.org/abs/2401.03048) from Monash University, Shanghai AI Lab, Nanjing University, and Nanyang Technological University.
+[Latte: Latent Diffusion Transformer for Video Generation](https://huggingface.co/papers/2401.03048) from Monash University, Shanghai AI Lab, Nanjing University, and Nanyang Technological University.
 
 The abstract from the paper is:
 
 *We propose a novel Latent Diffusion Transformer, namely Latte, for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In order to model a substantial number of tokens extracted from videos, four efficient variants are introduced from the perspective of decomposing the spatial and temporal dimensions of input videos. To improve the quality of generated videos, we determine the best practices of Latte through rigorous experimental analysis, including video clip patch embedding, model variants, timestep-class information injection, temporal positional embedding, and learning strategies. Our comprehensive evaluation demonstrates that Latte achieves state-of-the-art performance across four standard video generation datasets, i.e., FaceForensics, SkyTimelapse, UCF101, and Taichi-HD. In addition, we extend Latte to text-to-video generation (T2V) task, where Latte achieves comparable results compared to recent T2V models. We strongly believe that Latte provides valuable insights for future research on incorporating Transformers into diffusion models for video generation.*
 
-**Highlights**: Latte is a latent diffusion transformer proposed as a backbone for modeling different modalities (trained for text-to-video generation here). It achieves state-of-the-art performance across four standard video benchmarks - [FaceForensics](https://arxiv.org/abs/1803.09179), [SkyTimelapse](https://arxiv.org/abs/1709.07592), [UCF101](https://arxiv.org/abs/1212.0402) and [Taichi-HD](https://arxiv.org/abs/2003.00196). To prepare and download the datasets for evaluation, please refer to [this https URL](https://github.com/Vchitect/Latte/blob/main/docs/datasets_evaluation.md).
+**Highlights**: Latte is a latent diffusion transformer proposed as a backbone for modeling different modalities (trained for text-to-video generation here). It achieves state-of-the-art performance across four standard video benchmarks - [FaceForensics](https://huggingface.co/papers/1803.09179), [SkyTimelapse](https://huggingface.co/papers/1709.07592), [UCF101](https://huggingface.co/papers/1212.0402) and [Taichi-HD](https://huggingface.co/papers/2003.00196). To prepare and download the datasets for evaluation, please refer to [this https URL](https://github.com/Vchitect/Latte/blob/main/docs/datasets_evaluation.md).
 
 This pipeline was contributed by [maxin-cn](https://github.com/maxin-cn). The original codebase can be found [here](https://github.com/Vchitect/Latte). The original weights can be found under [hf.co/maxin-cn](https://huggingface.co/maxin-cn).