Table 1. Qualitative comparison between FrameBridge-CogVideoX and other diffusion I2V baselines. Name of pre-trained video diffusion models are specified in the brackets.

Static Image:	Text Condition:
	a hot-air balloon flying over a desert landscape
FrameBridge-CogVideoX (CogVideoX-2B):	DynamiCrafter (VideoCrafter1):
ConsistI2V (Inflated Stable Diffusion 2.1-Base):	SEINE (LaVie):

Table 2. Qualitative comparison between FrameBridge-CogVideoX and other diffusion I2V baselines. Name of pre-trained video diffusion models are specified in the brackets.

Static Image:	Text Condition:
	a blue fishing boat is navigating in the ocean next to a cruise ship
FrameBridge-CogVideoX (CogVideoX-2B):	DynamiCrafter (VideoCrafter1):
ConsistI2V (Inflated Stable Diffusion 2.1-Base):	SEINE (LaVie):

Table 3. Qualitative comparison between FrameBridge-CogVideoX and other diffusion I2V baselines. Name of pre-trained video diffusion models are specified in the brackets.

Static Image:	Text Condition:
	a bridge that is in the middle of a river, camera zooms out
FrameBridge-CogVideoX (CogVideoX-2B):	DynamiCrafter (VideoCrafter1):
ConsistI2V (Inflated Stable Diffusion 2.1-Base):	SEINE (LaVie):

Table 4. Qualitative comparison between FrameBridge-CogVideoX and other diffusion I2V baselines. Name of pre-trained video diffusion models are specified in the brackets.

Static Image:	Text Condition:
	a rabbit is playing the guitar
FrameBridge-CogVideoX (CogVideoX-2B):	DynamiCrafter (VideoCrafter1):
ConsistI2V (Inflated Stable Diffusion 2.1-Base):	SEINE (LaVie):

Table 5. Qualitative comparison between FrameBridge-CogVideoX and other diffusion I2V baselines. Name of pre-trained video diffusion models are specified in the brackets.

Static Image:	Text Condition:
	a building that is sitting on the side of a pond, camera pans right
FrameBridge-CogVideoX (CogVideoX-2B):	DynamiCrafter (VideoCrafter1):
ConsistI2V (Inflated Stable Diffusion 2.1-Base):	SEINE (LaVie):