This Pull Request also extends a video & uses end frame

.gitattributes

@@ -2,4 +2,9 @@
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.mp4 filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text 
+*.pth filter=lfs diff=lfs merge=lfs -text img_examples/Example1.png filter=lfs diff=lfs merge=lfs -text
+img_examples/Example2.webp filter=lfs diff=lfs merge=lfs -text
+img_examples/Example3.jpg filter=lfs diff=lfs merge=lfs -text
+img_examples/Example4.webp filter=lfs diff=lfs merge=lfs -text
+img_examples/Example5.png filter=lfs diff=lfs merge=lfs -text
+img_examples/Example6.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -4,8 +4,18 @@ emoji: 🎬
 colorFrom: indigo
 colorTo: purple
 sdk: gradio
-sdk_version:  5.29.0
+sdk_version: 5.29.1
 app_file: app.py
-pinned: false
-license: mit
+license: apache-2.0
+short_description: Text-to-Video/Image-to-Video/Video extender (timed prompt)
+tags:
+  - Image-to-Video
+  - Image-2-Video
+  - Img-to-Vid
+  - Img-2-Vid
+  - language models
+  - LLMs
+suggested_hardware: zero-a10g
 ---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

diffusers_helper/bucket_tools.py

@@ -15,6 +15,79 @@ bucket_options = {
         (864, 448),
         (960, 416),
     ],
+    672: [
+        (480, 864),
+        (512, 832),
+        (544, 768),
+        (576, 704),
+        (608, 672),
+        (640, 640),
+        (672, 608),
+        (704, 576),
+        (768, 544),
+        (832, 512),
+        (864, 480),
+    ],
+    704: [
+        (480, 960),
+        (512, 864),
+        (544, 832),
+        (576, 768),
+        (608, 704),
+        (640, 672),
+        (672, 640),
+        (704, 608),
+        (768, 576),
+        (832, 544),
+        (864, 512),
+        (960, 480),
+    ],
+    768: [
+        (512, 960),
+        (544, 864),
+        (576, 832),
+        (608, 768),
+        (640, 704),
+        (672, 672),
+        (704, 640),
+        (768, 608),
+        (832, 576),
+        (864, 544),
+        (960, 512),
+    ],
+    832: [
+        (544, 960),
+        (576, 864),
+        (608, 832),
+        (640, 768),
+        (672, 704),
+        (704, 672),
+        (768, 640),
+        (832, 608),
+        (864, 576),
+        (960, 544),
+    ],
+    864: [
+        (576, 960),
+        (608, 864),
+        (640, 832),
+        (672, 768),
+        (704, 704),
+        (768, 672),
+        (832, 640),
+        (864, 608),
+        (960, 576),
+    ],
+    960: [
+        (608, 960),
+        (640, 864),
+        (672, 832),
+        (704, 768),
+        (768, 704),
+        (832, 672),
+        (864, 640),
+        (960, 608),
+    ],
 }
 
 
@@ -26,5 +99,5 @@ def find_nearest_bucket(h, w, resolution=640):
         if metric <= min_metric:
             min_metric = metric
             best_bucket = (bucket_h, bucket_w)
+    print("The resolution of the generated video will be " + str(best_bucket))
     return best_bucket
-

img_examples/Example1.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a906a1d14d1699f67ca54865c7aa5857e55246f4ec63bbaf3edcf359e73bebd1
+size 240647

requirements.txt

@@ -1,18 +1,23 @@
-accelerate==1.6.0
-diffusers==0.33.1
-transformers==4.46.2
-sentencepiece==0.2.0
-pillow==11.1.0
-av==12.1.0
-numpy==1.26.2
-scipy==1.12.0
-requests==2.31.0
-torchsde==0.2.6
-torch>=2.0.0
-torchvision
-torchaudio
-einops
-opencv-contrib-python
-safetensors
-huggingface_hub
-spaces
+accelerate==1.7.0
+diffusers==0.33.1
+transformers==4.52.4
+sentencepiece==0.2.0
+pillow==11.2.1
+av==12.1.0
+numpy==1.26.2
+scipy==1.12.0
+requests==2.32.4
+torchsde==0.2.6
+torch>=2.0.0
+torchvision
+torchaudio
+einops
+opencv-contrib-python
+safetensors
+huggingface_hub
+decord
+imageio_ffmpeg==0.6.0
+sageattention==1.0.6
+xformers==0.0.29.post3
+bitsandbytes==0.46.0
+pillow-heif==0.22.0