magespace
/

hyvideo-diffusers

Diffusers

Safetensors

HunyuanVideoPipeline

Model card Files Files and versions

xet

Community

ghunkins commited on Dec 11, 2024

Commit

376630c

verified ·

1 Parent(s): 9648b42

Update README.md

Browse files

Files changed (1) hide show

README.md +51 -172

README.md CHANGED Viewed

@@ -2,197 +2,76 @@
 library_name: diffusers
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 library_name: diffusers
 ---
+# 👋 HyVideo
+This project is a first step in integrating [HunyuanVideo](https://github.com/Tencent/HunyuanVideo) into [Diffusers](https://github.com/huggingface/diffusers).
+**All credit go to [Tencent](https://github.com/Tencent) for the original [HunyuanVideo](https://github.com/Tencent/HunyuanVideo) project.**
+**Thank you to Huggingface for the [Diffusers](https://github.com/huggingface/diffusers) library.** Special shout-out to [@a-r-r-o-w](https://github.com/a-r-r-o-w) for his work on integrating HunyuanVideo.
+The License is inherted from [HunyuanVideo](https://github.com/Tencent/HunyuanVideo).
+This library is provided as-is and will be superseded by the official release of HunyuanVideo via [Diffusers](https://github.com/huggingface/diffusers). Please help out if you can on the [PR](https://github.com/huggingface/diffusers/pull/10136).
+## Installation
+```bash
+pip install git+https://github.com/ollanoinc/hyvideo.git
+```
+You will also need to install [flash-attn](https://github.com/Dao-AILab/flash-attention) for now.
+## Usage
+Please note that you need at least 80GB VRAM to run this pipeline. CPU offloading is having issues at the moment (PRs welcome!).
+```python
+import torch
+from hyvideo.diffusion.pipelines.pipeline_hunyuan_video import HunyuanVideoPipeline
+from hyvideo.modules.models import HYVideoDiffusionTransformer
+from hyvideo.vae.autoencoder_kl_causal_3d import AutoencoderKLCausal3D
+pipe = HunyuanVideoPipeline.from_pretrained(
+    'magespace/hyvideo-diffusers',
+    transformer=HYVideoDiffusionTransformer.from_pretrained(
+        'magespace/hyvideo-diffusers',
+        torch_dtype=torch.bfloat16,
+        subfolder='transformer'
+    ),
+    vae=AutoencoderKLCausal3D.from_pretrained(
+        'magespace/hyvideo-diffusers',
+        torch_dtype=torch.bfloat16,
+        subfolder='vae'
+    ),
+    torch_dtype=torch.bfloat16,
+)
+pipe = pipe.to('cuda')
+pipe.vae.enable_tiling()
+```
+Then running:
+```python
+prompt = "Close-up, A little girl wearing a red hoodie in winter strikes a match. The sky is dark, there is a layer of snow on the ground, and it is still snowing lightly. The flame of the match flickers, illuminating the girl's face intermittently."
+result = pipe(prompt)
+```
+Post-processing:
+```python
+import PIL.Image
+from diffusers.utils import export_to_video
+output = result.videos[0].permute(1, 2, 3, 0).detach().cpu().numpy()
+output = (output * 255).clip(0, 255).astype("uint8")
+output = [PIL.Image.fromarray(x) for x in output]
+export_to_video(output, "output.mp4", fps=24)
+```
+For faster generation, you can optimize the `transformer` with `torch.compile`. Additionally, increasing `shift` in the scheduler can allow for lower step values as shown in the original paper.
+Generation time is quadratic with the number of pixels, so reducing the height and width and decreasing the number of frames will drastically speed up generation at the price of video quality.