1. This workflow is the LTX2.3 image/text-to-video workflow, offering multiple configuration options (FP8 version, KJ version, GUFF version). The online version defaults to the FP8 version.

2. The best quality is still the original version. However, if using KJ's model (ltx 2.3 22b distilled_transformer_only_fp8_scaled), it is the optimal model for low configuration, speed, and high quality.

3. It is strongly recommended to use landscape mode. Portrait mode can generate results, but the effect is not ideal.

4. Auto-prompt words have been tested multiple times and can also be used to generate video prompts in other intelligent systems using prompt templates.

5. If I2V image-to-video is needed, turn on the switch.

6. Regarding resolution selection:

(1) LTX output video dimensions must be multiples of 32. Therefore, to ensure a video aspect ratio of 16:9, you can refer to the following dimensions: 512×288; 1024×576
(2) Other approximate 16:9 aspect ratios: 1920×1088
(3) Additionally, 1280×720/736 output videos will all be 1280×704
(4) 1280×768 can be output normally
(5) The higher the resolution, the better the effect, but the configuration requirements are higher

7. Default parameters (1280×736, 10 seconds) run once for about 80 points and take 7 minutes

Get free generation points: Click "Your avatar in the upper right corner" > Invitation code > Fill in the invitation code to get 1000 RH points for free. Log in daily to receive 100!

Invitation code: rh v1443