<h3 id="all-credit-goes-to:">All credit goes to:</h3><a target="_blank" rel="ugc" href="https://huggingface.co/Phr00t/LTX2-Rapid-Merges">Phr00t / LTX2‑Rapid‑Merges</a> and <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2">Lightricks / LTX‑2</a>I simply combined their workflows into a single pipeline that supports Image‑to‑Video, RIFE interpolation, and Latent Upscaling. The workflow includes NSFW models; however, SFW alternatives are available on Phr00t’s Hugging Face page.<h3 id="model-placement">Model Placement</h3><ul><li>Diffusion model: <code>\diffusion_models</code></li><li>Video VAE: <code>\vae</code></li><li>Audio VAE: <code>\checkpoints</code></li><li>Text encoder: <code>\text_encoders</code></li><li>Upscaler: <code>\latent_upscale_models</code></li></ul>Edit: Feel free to delete any custom nodes in the Optional Group if you don't need them.<h3 id="v3.0-update-notes">V3.0 Update Notes</h3><ul><li>Bug Fixes: Resolved issues by adding the missing <code>LTXVCropGuides</code> node. If your customized workflow is glitching, adding this node will noticeably improve stability.</li><li>Automation: Added automatic aspect ratio detection and automatic dimension rounding to multiples of 64.</li><li>LoRA Support: A LoRA chain has been added as an example inside the Samples section.<ul><li>Crucial: Ensure both samplers use the exact same internal configuration; only the external values should differ. This is necessary to avoid visual artifacts.</li></ul></li><li>Final Note: This may be my last update for this project. Thanks for the support!</li></ul><h3 id="v2.5-update-notes-disclaimer:-this-is-essentially-the-original-lightricks-workflow.-i've-worked-hard-to-find-more-reliable-settings-but-this-is-the-best-result-so-far-i've-mainly-removed-dependencies-and-reorganized-the-nodes.">V2.5 Update Notes Disclaimer: This is essentially the original Lightricks workflow. I’ve worked hard to find more reliable settings, but this is the best result so far, I've mainly removed dependencies and reorganized the nodes.</h3>Most artifacts are caused by the Strength settings, the prompt, or the source image. As shown in the video example, glitches don't occur every time, but some images are more prone to them than others. Here are some tips to avoid these issues:<ul><li>Adjust Strength: Avoid using full strength. Experiment with different values for Stage 1 and Stage 2; every LoRA requires specific tweaking.</li><li>Tweak Compression: For high-motion videos, try increasing the compression. If the video looks stable, you can lower it to improve sharpness.</li><li>Frame Rate: Generally, a higher frame rate leads to better stability.</li><li>Resolution &amp; Upscaling: Note that the Resolution and Frame Rate settings represent the processing values. The final video output will be twice the size of these inputs.</li><li>Final Troubleshooting: If the above tips don't work, try changing the prompt, the seed, or as a last resort, the source image itself.</li></ul>The workflow includes the wrong link to optionally download Gemma, this is the correct link:<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/mlabonne/gemma-3-12b-it-abliterated-GGUF">mlabonne/gemma-3-12b-it-abliterated-GGUF · Hugging Face</a></li></ul><h3 id="v2.0-update-notes">V2.0 Update Notes</h3>LoRA Support &amp; Resolution: This version adds LoRA support, optimized for 720p. While I aimed for 1080p, 720p currently provides the most stable results and better visual coherence when using LoRAs.What to expect:<ul><li>Better Consistency: LoRA details are more reliable at this resolution.</li><li>Fluidity: The 8-sigma process is fast and works great for standard motion.</li><li>Audio Sync: 720p ensures the best synchronization between audio and video.</li></ul>Note: This update is the result of many trials to balance quality and stability. I’ll keep working on a high-resolution version for future releases.Edit: update sigmas from 8 to 12 as <code>1.0, 0.98, 0.96, 0.94, 0.91, 0.87, 0.82, 0.75, 0.55, 0.35, 0.15, 0.0</code><h3 id="performance">Performance</h3>Rendering a 5‑second video 1024x1400@30fps takes approximately 2 minutes on a system with 16 GB of VRAM.<h3 id="licensing-and-usage">Licensing &amp; Usage</h3>All usage rights, licenses, and permissions are governed by the original authors. Please refer to the official source pages and repositories for the applicable terms and conditions.For detailed instructions and model usage, please consult the original workflows and documentation provided by the authors.

Files with SHA256: 66270cebee01c6afcbe187e5b6ed59d3aca17ed2b4ce03e62cce9dd9913060d9