User Manual for LTX2.3 Audio-Visual Driven Digital Human Workflow
1. The online workflow uses the LTX-2.3-22b-dev-fp8 model, and the local version can be adjusted according to your hardware configuration. It is confirmed that the Q4.gguf model is fully compatible with 12GB VRAM.
2. Pay attention to the notes next to the model when making adjustments and ensure correct node connections.
3. KJ's model offers the best cost-performance ratio for balancing low hardware requirements, fast generation speed and high output quality. The GGUF version has the lowest configuration demands, while the LTX-2.3-22b-dev-fp8 model delivers the best visual effects.
4. Specific rules apply to resolution selection; see the notes next to the resolution settings for details. Landscape mode is highly recommended—portrait mode is supported for generation but will produce subpar results.
5. Test conditions: Generating a 10-second image-to-video at 1280×736 resolution on a test PC with RTX 5060 Ti 16G + 32G RAM.
- ltx-2.3-22b-distilled_transformer_only_fp8_scaled: 335s
- ltx-2.3-22b-dev: 20min
- LTX-2.3-22b-dev-fp8: 500s
- LTX-2.3-22b-dev-Q4_K_M.gguf: 430s
- LTX-2.3-22b-dev-Q8_0.gguf: 470s
6. The auto-generated prompts have been repeatedly tested and can also be used with prompt templates to generate video prompts in other AI agents.
7. For audio-driven generation, the end time shall be subject to the video duration after uploading the audio file.
8. Auto-generated prompts have little impact on the audio-driven generation effect; you can disconnect the auto-prompt link and fill in custom prompts manually.
Resolution Selection Guidelines
（1）The output video dimensions of LTX must be multiples of 32. For a strict 16:9 aspect ratio, refer to the following resolutions: 512×288; 1024×576.
（2）Other approximate 16:9 resolutions: 1920×1088.
（3）Input resolutions of 1280×720/736 will both output a video of 1280×704.
（4）1280×768 is a fully supported resolution for normal output.
（5）Higher resolutions yield better visual effects but require more powerful hardware configurations.
Model download links are provided in the workflow.
This workflow is available for free online testing—download it for local use only if you are satisfied with the results.
Test URL: https://www.runninghub.ai/post/2027025326320128001/?inviteCode=rh-v1443
Bonus Points: 1000 points for new registrations, 100 points for daily login. A single generation with the above test parameters consumes only 80 points.