fix: video rendering on svd.

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

@@ -38,21 +38,16 @@ The following example demonstrates how to use a *MotionAdapter* checkpoint with
 
 ```python
 import torch
-from diffusers import AnimateDiffPipeline, DDIMScheduler, MotionAdapter
+from diffusers import MotionAdapter, AnimateDiffPipeline, DDIMScheduler
 from diffusers.utils import export_to_gif
 
 # Load the motion adapter
-adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", torch_dtype=torch.float16)
+adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2")
 # load SD 1.5 based finetuned model
 model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
-pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter, torch_dtype=torch.float16)
+pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter)
 scheduler = DDIMScheduler.from_pretrained(
-    model_id,
-    subfolder="scheduler",
-    clip_sample=False,
-    timestep_spacing="linspace",
-    beta_schedule="linear",
-    steps_offset=1,
+    model_id, subfolder="scheduler", clip_sample=False, timestep_spacing="linspace", steps_offset=1
 )
 pipe.scheduler = scheduler
 
@@ -75,7 +70,6 @@ output = pipe(
 )
 frames = output.frames[0]
 export_to_gif(frames, "animation.gif")
-
 ```
 
 Here are some sample outputs:
@@ -94,7 +88,7 @@ Here are some sample outputs:
 
 <Tip>
 
-AnimateDiff tends to work better with finetuned Stable Diffusion models. If you plan on using a scheduler that can clip samples, make sure to disable it by setting `clip_sample=False` in the scheduler as this can also have an adverse effect on generated samples. Additionally, the AnimateDiff checkpoints can be sensitive to the beta schedule of the scheduler. We recommend setting this to `linear`.
+AnimateDiff tends to work better with finetuned Stable Diffusion models. If you plan on using a scheduler that can clip samples, make sure to disable it by setting `clip_sample=False` in the scheduler as this can also have an adverse effect on generated samples.
 
 </Tip>
 
@@ -104,25 +98,18 @@ Motion LoRAs are a collection of LoRAs that work with the `guoyww/animatediff-mo
 
 ```python
 import torch
-from diffusers import AnimateDiffPipeline, DDIMScheduler, MotionAdapter
+from diffusers import MotionAdapter, AnimateDiffPipeline, DDIMScheduler
 from diffusers.utils import export_to_gif
 
 # Load the motion adapter
-adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", torch_dtype=torch.float16)
+adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2")
 # load SD 1.5 based finetuned model
 model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
-pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter, torch_dtype=torch.float16)
-pipe.load_lora_weights(
-    "guoyww/animatediff-motion-lora-zoom-out", adapter_name="zoom-out"
-)
+pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter)
+pipe.load_lora_weights("guoyww/animatediff-motion-lora-zoom-out", adapter_name="zoom-out")
 
 scheduler = DDIMScheduler.from_pretrained(
-    model_id,
-    subfolder="scheduler",
-    clip_sample=False,
-    beta_schedule="linear",
-    timestep_spacing="linspace",
-    steps_offset=1,
+    model_id, subfolder="scheduler", clip_sample=False, timestep_spacing="linspace", steps_offset=1
 )
 pipe.scheduler = scheduler
 
@@ -145,7 +132,6 @@ output = pipe(
 )
 frames = output.frames[0]
 export_to_gif(frames, "animation.gif")
-
 ```
 
 <table>
@@ -174,30 +160,21 @@ Then you can use the following code to combine Motion LoRAs.
 
 ```python
 import torch
-from diffusers import AnimateDiffPipeline, DDIMScheduler, MotionAdapter
+from diffusers import MotionAdapter, AnimateDiffPipeline, DDIMScheduler
 from diffusers.utils import export_to_gif
 
 # Load the motion adapter
-adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", torch_dtype=torch.float16)
+adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2")
 # load SD 1.5 based finetuned model
 model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
-pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter, torch_dtype=torch.float16)
+pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter)
 
-pipe.load_lora_weights(
-    "diffusers/animatediff-motion-lora-zoom-out", adapter_name="zoom-out",
-)
-pipe.load_lora_weights(
-    "diffusers/animatediff-motion-lora-pan-left", adapter_name="pan-left",
-)
+pipe.load_lora_weights("diffusers/animatediff-motion-lora-zoom-out", adapter_name="zoom-out")
+pipe.load_lora_weights("diffusers/animatediff-motion-lora-pan-left", adapter_name="pan-left")
 pipe.set_adapters(["zoom-out", "pan-left"], adapter_weights=[1.0, 1.0])
 
 scheduler = DDIMScheduler.from_pretrained(
-    model_id,
-    subfolder="scheduler",
-    clip_sample=False,
-    timestep_spacing="linspace",
-    beta_schedule="linear",
-    steps_offset=1,
+    model_id, subfolder="scheduler", clip_sample=False, timestep_spacing="linspace", steps_offset=1
 )
 pipe.scheduler = scheduler
 
@@ -220,7 +197,6 @@ output = pipe(
 )
 frames = output.frames[0]
 export_to_gif(frames, "animation.gif")
-
 ```
 
 <table>

docs/source/en/using-diffusers/svd.md

@@ -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)
@@ -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.
@@ -120,7 +125,7 @@ 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)
@@ -128,7 +133,5 @@ frames = pipe(image, decode_chunk_size=8, generator=generator, motion_bucket_id=
 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)