Video Models

text to video

single-shot-video generation

✅（only 5s、10s）

✅（only 5s、10s）

voice control

❌

❌

others

-

-

image to video

single-shot-video generation

（only start frame）

✅（only 5s、10s）

✅（only 5s、10s）

start & end frame

✅

✅

element control

（only multi-image elements）

✅

✅

cideo reference

(including multi-image elements)

✅

✅

voice control

❌

❌

others

-

-

text to video

single-shot-video generation

✅

✅

multi-shot-video generation

✅

✅

voice control

❌

❌

others

-

-

image to video

single-shot-video generation

✅

✅

multi-shot-video generation

✅

✅

start & end frame

✅

✅

element control

（video character elements & multi-image elements）

✅

✅

reference video

✅（only 3s～10s）

✅（only 3s～10s）

voice control

❌

❌

others

-

-

text

to video

video generation

✅

✅

✅

✅

camera control

✅

-

-

-

image

to video

video generation

✅

✅

✅

✅

start/end frame

✅

-

✅

-

motion brush

✅

-

✅

-

others

-

-

-

-

video extension

（Not supported negative_prompt and cfg_scale)

✅

✅

✅

✅

video effects

Dual-character: Hug, Kiss, heart_gesture

✅

✅

✅

✅

others

-

-

-

-

text

to video

video generation

-

-

-

-

others

-

-

-

-

image

to video

video generation

✅

✅

✅

✅

start/end frame

-

-

✅

✅

end frame

-

-

✅

✅

motion brush

-

-

✅

-

camera control

（simple only）

-

-

✅

-

others

-

-

-

-

video extension

✅

✅

✅

✅

video effects

Dual-character: Hug, Kiss, heart_gesture

✅

✅

✅

✅

others

-

-

-

-

text

to video

video generation

✅

✅

✅

✅

others

-

-

-

-

image

to video

video generation

✅

✅

✅

✅

start/end frame

-

-

✅

✅

end frame

-

-

✅

✅

others

-

-

-

-

multi-image2video

✅

✅

✅

✅

multi-elements

✅

✅

✅

✅

video extension

✅

✅

✅

✅

video effects

Dual-character: Hug, Kiss, heart_gesture

✅

✅

✅

✅

text

to video

video generation

✅

✅

others

-

-

image

to video

video generation

✅

✅

others

-

-

others

-

-

text

to video

all

-

-

-

-

image

to video

video generation

✅

✅

✅

✅

start/end frame

-

-

✅

✅

others

-

-

-

-

others

-

-

-

-

text

to video

video generation

✅

✅

others

-

-

image

to video

video generation

✅

✅

others

-

-

others

-

-

text

to video

video generation

✅

✅

✅

✅

others

-

-

-

-

image

to video

video generation

✅

✅

✅

✅

start/end frame

-

-

✅

✅

others

-

-

-

-

others

-

-

-

-

text to video

video generation

✅ (only no audio)

✅ (only no audio)

-

✅

✅

-

others

-

-

-

-

-

-

image to video

video generation

✅ (only no audio)

✅ (only no audio)

-

✅

✅

-

start/end frame

-

-

-

✅ (only no audio)

✅ (only no audio)

-

voice control

-

-

-

✅

✅

-

motion control

-

-

✅

-

-

✅

others

-

-

-

-

-

-

text to video

single-shot-video generation

✅

✅

multi-shot-video generation

✅

✅

voice control

❌

❌

others

-

-

image to video

single-shot-video generation （only start frame）

✅

✅

multi-shot-video generation

✅

✅

start & end frame

✅

✅

element control

（video character elements & multi-image elements）

✅

✅

motion control

✅

✅

voice control

❌

❌

others

-

-

avatar

✅

Generate digital human broadcast-style videos with just one photo

lip sync

✅

Can be combined with text or audio to drive the mouth shape of characters in the video

video to audio

✅

Supports adding audio to all videos generated by Kling models and user-uploaded videos

text to audio

-

Supports generating audio by text prompts

others

-

-

Mode

STD

PRO

STD

PRO

STD

PRO

STD

PRO

-

Resolution

720p

720p

720p

1080p

720p

1080p

720p

1080p

720p

Frame Rate

30fps

30fps

30fps

30fps

30fps

30fps

24fps

24fps

24fps

Mode

STD

PRO

-

PRO

PRO

Resolution

720p

1080p

1080p

1080p

1080p

Frame Rate

24fps

24fps

24fps

24fps

24fps