[Admin maintenance] Support new ZeroGPU hardware

README.md

@@ -4,7 +4,7 @@ emoji: 🐨
 colorFrom: indigo
 colorTo: pink
 sdk: gradio
-sdk_version: 4.37.1
+sdk_version: 6.20.0
 app_file: app.py
 pinned: false
 license: apache-2.0

app.py

@@ -1,14 +1,31 @@
+import spaces
 import os
+# The 2.0 rewrite of DiffSynth-Studio restructured the package into diffsynth/core/...
+# and dropped ModelManager/SVDVideoPipeline (and requirements.txt), breaking the runtime
+# `git clone` + `pip install -r DiffSynth-Studio/requirements.txt` this Space used to do.
+# Pin the clone to the last pre-2.0 commit. All of DiffSynth's own deps (torch, transformers,
+# huggingface_hub, einops, etc.) are now pinned directly in this Space's requirements.txt and
+# installed at BUILD time, so at runtime we only need to fetch and copy the plain-Python
+# `diffsynth` package itself (no pip install here: `import spaces` above already pulled
+# huggingface_hub into memory, so a runtime `pip install --upgrade` would update the files on
+# disk but not the module object already cached in this process's sys.modules).
 os.system("git clone https://github.com/modelscope/DiffSynth-Studio.git")
+os.system("cd DiffSynth-Studio && git checkout afd101f3452c9ecae0c87b79adfa2e22d65ffdc3")
 os.system("cp -r DiffSynth-Studio/diffsynth ./")
-os.system("pip install -r DiffSynth-Studio/requirements.txt")
+# gradio 6 needs huggingface_hub>=1.2, but this pre-2.0 DiffSynth checkout needs a
+# huggingface_hub new enough to satisfy modern transformers (CachedRepoTreeNotFoundError) --
+# together that only resolves with a 5.x transformers, which dropped the long-deprecated
+# re-export `transformers.modeling_utils.PretrainedConfig` that diffsynth's
+# stepvideo_text_encoder.py still imports. Shim it back before diffsynth is imported.
+import transformers.modeling_utils as _modeling_utils
+from transformers.configuration_utils import PretrainedConfig as _PretrainedConfig
+if not hasattr(_modeling_utils, "PretrainedConfig"):
+    _modeling_utils.PretrainedConfig = _PretrainedConfig
 from diffsynth import save_video, ModelManager, SVDVideoPipeline
-from diffsynth import ModelManager
-import torch, os, random, time
+import torch, random, time
 import gradio as gr
 import numpy as np
 from PIL import Image
-import spaces
 
 
 def get_i2v_pipeline():
@@ -99,7 +116,7 @@ To use this model, please refer to [DiffSynth](https://github.com/modelscope/Dif
         inputs=image,
         outputs=[video, seed],
         fn=process_examples,
-        cache_examples="lazy",
+        cache_examples=False,
     )
 
 if __name__ == "__main__":

requirements.txt

@@ -0,0 +1,16 @@
+torch==2.11.0
+torchvision==0.26.0
+huggingface_hub==1.23.0
+transformers
+imageio
+imageio[ffmpeg]
+safetensors
+einops
+sentencepiece
+protobuf
+modelscope
+ftfy
+pynvml
+pandas
+accelerate
+peft