more fixes

Author: sayakpaul

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

@@ -11,7 +11,7 @@ specific language governing permissions and limitations under the License. -->
 
 # AutoencoderKLHunyuanVideo
 
-The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanVideo](https://github.com/Tencent/HunyuanVideo/), which was introduced in [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://huggingface.co/papers/2412.03603) by Tencent.
+The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanVideo](https://github.com/hunyuanvideo-community/HunyuanVideo/), which was introduced in [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://huggingface.co/papers/2412.03603) by Tencent.
 
 The model can be loaded with the following code snippet.
 

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

@@ -16,7 +16,7 @@
 
 [HunyuanVideo](https://www.arxiv.org/abs/2412.03603) by Tencent.
 
-*Recent advancements in video generation have significantly impacted daily life for both individuals and industries. However, the leading video generation models remain closed-source, resulting in a notable performance gap between industry capabilities and those available to the public. In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models. HunyuanVideo encompasses a comprehensive framework that integrates several key elements, including data curation, advanced architectural design, progressive model scaling and training, and an efficient infrastructure tailored for large-scale model training and inference. As a result, we successfully trained a video generative model with over 13 billion parameters, making it the largest among all open-source models. We conducted extensive experiments and implemented a series of targeted designs to ensure high visual quality, motion dynamics, text-video alignment, and advanced filming techniques. According to evaluations by professionals, HunyuanVideo outperforms previous state-of-the-art models, including Runway Gen-3, Luma 1.6, and three top-performing Chinese video generative models. By releasing the code for the foundation model and its applications, we aim to bridge the gap between closed-source and open-source communities. This initiative will empower individuals within the community to experiment with their ideas, fostering a more dynamic and vibrant video generation ecosystem. The code is publicly available at [this https URL](https://github.com/Tencent/HunyuanVideo).*
+*Recent advancements in video generation have significantly impacted daily life for both individuals and industries. However, the leading video generation models remain closed-source, resulting in a notable performance gap between industry capabilities and those available to the public. In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models. HunyuanVideo encompasses a comprehensive framework that integrates several key elements, including data curation, advanced architectural design, progressive model scaling and training, and an efficient infrastructure tailored for large-scale model training and inference. As a result, we successfully trained a video generative model with over 13 billion parameters, making it the largest among all open-source models. We conducted extensive experiments and implemented a series of targeted designs to ensure high visual quality, motion dynamics, text-video alignment, and advanced filming techniques. According to evaluations by professionals, HunyuanVideo outperforms previous state-of-the-art models, including Runway Gen-3, Luma 1.6, and three top-performing Chinese video generative models. By releasing the code for the foundation model and its applications, we aim to bridge the gap between closed-source and open-source communities. This initiative will empower individuals within the community to experiment with their ideas, fostering a more dynamic and vibrant video generation ecosystem. The code is publicly available at [this https URL](https://github.com/hunyuanvideo-community/HunyuanVideo).*
 
 <Tip>
 
@@ -30,7 +30,7 @@ Recommendations for inference:
 - VAE should be in `torch.float16`.
 - `num_frames` should be of the form `4 * k + 1`, for example `49` or `129`.
 - For smaller resolution videos, try lower values of `shift` (between `2.0` to `5.0`) in the [Scheduler](https://huggingface.co/docs/diffusers/main/en/api/schedulers/flow_match_euler_discrete#diffusers.FlowMatchEulerDiscreteScheduler.shift). For larger resolution images, try higher values (between `7.0` and `12.0`). The default value is `7.0` for HunyuanVideo.
-- For more information about supported resolutions and other details, please refer to the original repository [here](https://github.com/Tencent/HunyuanVideo/).
+- For more information about supported resolutions and other details, please refer to the original repository [here](https://github.com/hunyuanvideo-community/HunyuanVideo/).
 
 ## Quantization
 

docs/source/en/using-diffusers/text-img2vid.md

@@ -70,18 +70,18 @@ export_to_video(video, "output.mp4", fps=8)
 > [!TIP]
 > HunyuanVideo is a 13B parameter model and requires a lot of memory. Refer to the HunyuanVideo [Quantization](../api/pipelines/hunyuan_video#quantization) guide to learn how to quantize the model. CogVideoX and LTX-Video are more lightweight options that can still generate high-quality videos.
 
-[HunyuanVideo](https://huggingface.co/tencent/HunyuanVideo) features a dual-stream to single-stream diffusion transformer (DiT) for learning video and text tokens separately, and then subsequently concatenating the video and text tokens to combine their information. A single multimodal large language model (MLLM) serves as the text encoder, and videos are also spatio-temporally compressed with a 3D causal VAE.
+[HunyuanVideo](https://huggingface.co/hunyuanvideo-community/HunyuanVideo) features a dual-stream to single-stream diffusion transformer (DiT) for learning video and text tokens separately, and then subsequently concatenating the video and text tokens to combine their information. A single multimodal large language model (MLLM) serves as the text encoder, and videos are also spatio-temporally compressed with a 3D causal VAE.
 
 ```py
 import torch
 from diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel
 from diffusers.utils import export_to_video
 
 transformer = HunyuanVideoTransformer3DModel.from_pretrained(
-    "tencent/HunyuanVideo", subfolder="transformer", torch_dtype=torch.bfloat16
+    "hunyuanvideo-community/HunyuanVideo", subfolder="transformer", torch_dtype=torch.bfloat16
 )
 pipe = HunyuanVideoPipeline.from_pretrained(
-  "tencent/HunyuanVideo", transformer=transformer, torch_dtype=torch.float16
+  "hunyuanvideo-community/HunyuanVideo", transformer=transformer, torch_dtype=torch.float16
 )
 
 # reduce memory requirements

src/diffusers/models/transformers/transformer_hunyuan_video.py

@@ -504,7 +504,8 @@ def forward(
 
 class HunyuanVideoTransformer3DModel(ModelMixin, ConfigMixin, PeftAdapterMixin, FromOriginalModelMixin):
     r"""
-    A Transformer model for video-like data used in [HunyuanVideo](https://huggingface.co/tencent/HunyuanVideo).
+    A Transformer model for video-like data used in
+    [HunyuanVideo](https://huggingface.co/hunyuanvideo-community/HunyuanVideo).
 
     Args:
         in_channels (`int`, defaults to `16`):