This workflow is a modular and flexible text/image/audio-to-video generation system built in ComfyUI, designed to give full control over video creation using LTX-based models. It allows you to easily switch between multiple generation modes—such as text-to-video, image-to-video, lipsync, and fully guided animation—by enabling or disabling grouped nodes.The pipeline supports advanced features including LoRA-based character and style conditioning, voice identity transfer (ID LoRA), custom or generated audio, and ControlNet-guided animation using reference videos. Users can also incorporate keyframe images for structured motion control or rely on a single reference image for consistent character appearance.Performance and quality can be balanced through options like half-resolution sampling with 2× upscaling, as well as post-processing tools like the LTX detailer.<h2 id="main-features">Main features</h2><ul><li>GGUF support</li><li>Prompt relay for segmented prompts</li><li>Modular, toggle-based workflow (quickly switch modes)</li><li>Text, image, audio, and ControlNet-driven video generation</li><li>LoRA support (character, style, and voice via ID LoRA)</li><li>Custom or AI-generated audio with automatic syncing</li><li>Reference image + up to 7 keyframes (FFLF animation control)</li><li>ControlNet video guidance with hybrid reference support</li><li>Half-res sampling + 2× upscaling for faster high-quality results</li><li>LTX detailer for enhanced final output</li></ul><h2 id="common-setups">Common Setups</h2><ul><li>Text to video: All bypassers disabled + Prompt + Default audio</li><li>Image to video: Prompt + Reference image + Default audio</li><li>Lipsync: Prompt + Reference image + Custom audio</li><li>Audio to video: Prompt + Custom audio only</li><li>Character LoRA + voice cloning: Prompt + Character LoRA + ID LoRA + Default audio</li><li>Voice reference to video: Prompt + ID LoRA + Default audio OR Prompt + ID LoRA + Reference image + Default audio</li><li>Character animation: Prompt + ControlNet + Reference image + (Custom or Default audio)</li><li>First frame → last frame: Prompt + Keyframe 1 + Keyframe 2 + (Custom or Default audio)</li><li>First → middle → last frame: Prompt + Keyframe 1 + Keyframe 2 + Keyframe 3 + (Custom or Default audio)</li><li>Character animation with custom voice: Prompt + Reference image + ID LoRA + ControlNet + Default audio</li></ul>Detailed instructions are contained in the workflow itself:<ul><li>Red nodes are instructions and useful notes.</li><li>Yellow nodes are configurable elements you can adjust to your needs.</li></ul><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/88ff9b95-93a5-46fc-b370-96c239a00a6a/original=true/88ff9b95-93a5-46fc-b370-96c239a00a6a.jpeg" />

LTX2.3 All in one - Prompt Relay + ID LoRA + ControlNet + Detailer + Upscaler + Custom Audio + Keyframes

- Added LTX2.3 1.1 support. - Added Prompt relay support. - Added extra keyframes (now 8 in total). - Enhanced the upscaling process; now all the keyframes are taken as reference for upscaling, not just the first one.

Files with SHA256: 47fac04ebfdf64df992622d6e5a59bc7a505ad6e04a0e04af0df6af5a0331095