Current Model

LTX 2.3 Quality
LTX 2.3 Quality

Videogen

High-fidelity I2V/T2V with LTX 2.3 Quality — prompt control, optional audio, resolution presets, and image strength for I2V.

Quick Navigation

Prompt *

Field Description: The prompt to guide the video generation. Voice tips: To use the voice feature, you need to click on the microphone icon. You need to have a microphone connected to your computer. The voice feature uses 0.5 tokens per audio usage. Current language: English. Please change the language at the bottom if you are speaking in a different language. Multilingual support: GenVR supports multiple languages. If you are prompting in any language besides english, make sure the language setting in the bottom of the page is set to correct language.

Starting image

Optional reference image for image-to-video. Leave empty for text-to-video.

Output sizeauto

Output video size preset. Choose custom to set width and height. Width and height must match API limits.

Width (custom)1280

Custom output width in pixels. Used when size is custom.

Height (custom)720

Custom output height in pixels. Used when size is custom.

Number of frames121

9

481

How many frames to generate (9–481).

Frames per second24

1

60

FPS of the generated video (1–60).

Inference steps15

8

30

Number of inference steps (8–30). Default 15 for the distilled workflow.

Guidance scale1

1

20

Classifier-free guidance scale (1–20).

Generate audioEnabled

Include audio in the returned video. When disabled, the MP4 has no audio track.

Image strength0.7

0

1

Conditioning strength on the start image. 1.0 = exact first-frame match; lower values give the model more freedom.

Negative prompt395 chars

Steer generation away from unwanted artifacts and styles.

Enable prompt expansionEnabled

Automatically expand the prompt for richer results.

Video qualityhigh

Quality preset for the encoded output.

Video write modebalanced

Encoding write mode tradeoff.

Seed0

Random seed for reproducibility. Leave empty for a random seed.

Please provide all required parameters (* marked)

0.24075 credits per megapixel of generated video (width × height × frames), rounded up. Example: 121 frames at 1280×720 ≈ 112 MP → 27 credits. Auto size uses source image dimensions when available. Frames: 9–481.

View Past Creations
No Output Yet