Merge branch 'main' of https://huggingface.co/spaces/TIGER-Lab/GenAI-Arena

model/model_registry.py

@@ -194,6 +194,13 @@ register_model_info(
     "AnimateDiff is a text-driven models that produce diverse and personalized animated images.",
 )
 
+register_model_info(
+    ["fal_StableVideoDiffusion_text2video"],
+    "StableVideoDiffusion",
+    "https://fal.ai/models/fal-ai/fast-svd/text-to-video/api",
+    "Stable Video Diffusion empowers individuals to transform text and image inputs into vivid scenes.",
+)
+
 register_model_info(
     ["fal_AnimateDiffTurbo_text2video"],
     "AnimateDiff Turbo",

model/models/__init__.py

@@ -11,8 +11,8 @@ IMAGE_EDITION_MODELS = ['imagenhub_CycleDiffusion_edition', 'imagenhub_Pix2PixZe
                         'imagenhub_SDEdit_edition', 'imagenhub_InstructPix2Pix_edition', 
                         'imagenhub_MagicBrush_edition', 'imagenhub_PNP_edition', 
                         'imagenhub_InfEdit_edition', 'imagenhub_CosXLEdit_edition']
-VIDEO_GENERATION_MODELS = ['fal_AnimateDiff_text2video',
-                           'fal_AnimateDiffTurbo_text2video',
+VIDEO_GENERATION_MODELS = ['fal_AnimateDiff_text2video', 'fal_AnimateDiffTurbo_text2video',
+                           #'fal_StableVideoDiffusion_text2video',
                            'videogenhub_LaVie_generation', 'videogenhub_VideoCrafter2_generation',
                            'videogenhub_ModelScope_generation', 'videogenhub_OpenSora_generation']
 

model/models/fal_api_models.py

@@ -77,6 +77,8 @@ class FalModel():
                 fal_model_name = 'fast-animatediff/text-to-video'
             elif self.model_name == 'AnimateDiffTurbo':
                 fal_model_name = 'fast-animatediff/turbo/text-to-video'
+            elif self.model_name == 'StableVideoDiffusion':
+                fal_model_name = 'fast-svd/text-to-video'
             else:
                 raise NotImplementedError(f"text2video model of {self.model_name} in fal is not implemented yet")
             handler = fal_client.submit(