Skip to content

Commit

Permalink
[Docs] fix: video rendering on svd. (huggingface#6330)
Browse files Browse the repository at this point in the history
fix: video rendering on svd.
  • Loading branch information
sayakpaul authored and donhardman committed Dec 29, 2023
1 parent a125f5d commit 2759f3d
Showing 1 changed file with 8 additions and 5 deletions.
13 changes: 8 additions & 5 deletions docs/source/en/using-diffusers/svd.md
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ pipe = StableVideoDiffusionPipeline.from_pretrained(
pipe.enable_model_cpu_offload()

# Load the conditioning image
image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png?download=true")
image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png")
image = image.resize((1024, 576))

generator = torch.manual_seed(42)
Expand All @@ -58,6 +58,11 @@ export_to_video(frames, "generated.mp4", fps=7)
<source src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket_generated.mp4" type="video/mp4" />
</video>

| **Source Image** | **Video** |
|:------------:|:-----:|
| ![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png) | ![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/output_rocket.gif) |


<Tip>
Since generating videos is more memory intensive we can use the `decode_chunk_size` argument to control how many frames are decoded at once. This will reduce the memory usage. It's recommended to tweak this value based on your GPU memory.
Setting `decode_chunk_size=1` will decode one frame at a time and will use the least amount of memory but the video might have some flickering.
Expand Down Expand Up @@ -120,15 +125,13 @@ pipe = StableVideoDiffusionPipeline.from_pretrained(
pipe.enable_model_cpu_offload()

# Load the conditioning image
image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png?download=true")
image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png")
image = image.resize((1024, 576))

generator = torch.manual_seed(42)
frames = pipe(image, decode_chunk_size=8, generator=generator, motion_bucket_id=180, noise_aug_strength=0.1).frames[0]
export_to_video(frames, "generated.mp4", fps=7)
```

<video width="1024" height="576" controls>
<source src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket_generated_motion.mp4" type="video/mp4">
</video>
![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/output_rocket_with_conditions.gif)

0 comments on commit 2759f3d

Please sign in to comment.