<h2 id="ltx22.3-text-to-video-simple-workflow">✨ LTX2/2.3 — Text to video — Simple Workflow</h2>A clean, all-in-one LTX2 text-to-video workflow built entirely with the UmeAiRT Toolkit for ComfyUI. Only 12 nodes. No spaghetti wires. Just load your model, write your prompt, and hit generate.<hr /><h3 id="important-nodes-2.0-required">⚠️ IMPORTANT — Nodes 2.0 Required</h3>This workflow is built for the Nodes 2.0 (Vue) interface of ComfyUI. If you don't enable it, the workflow may have display problems.How to activate Nodes 2.0:<ol><li>Open ComfyUI</li><li>Go to Settings (⚙️ icon, bottom-left)</li><li>Find "Use Nodes V2 (Vue)" and toggle it ON</li><li>Refresh the page</li><li>Load the workflow</li></ol>If you prefer the classic interface, check out my Legacy version of this workflow instead (<a target="_blank" rel="ugc" href="https://civarchive.com/models/2329559/ltx2txt-to-video?modelVersionId=2620518">link</a>).<hr /><h2 id="features">🎯 Features</h2><ul><li>Text-to-Image generation</li><li>Automatic download of models in auto version</li><li>Built-in SeedVR2 upscaler — high-quality tiled upscaling (toggleable on/off) Slower than a classic upscaler, but significantly better quality</li><li>Full metadata embedding — your images are saved with all generation parameters, ready for online publishing and remixing</li><li>3 LoRA slots — with individual on/off toggles and strength control and you can connect as many other lora modules to each other for as many LoRA as you want.</li></ul><hr /><h2 id="custom-node-required">📦 Custom Node Required</h2>Only one custom node to install:👉 <a target="_blank" rel="ugc" href="https://gitlab.com/UmeAiRT-Studio/ComfyUI-UmeAiRT-Toolkit">ComfyUI-UmeAiRT-Toolkit</a>Install via ComfyUI Manager (search "UmeAiRT") or use the UmeAiRT Auto-Installer. The Toolkit packages everything internally — upscaler, face detailer, metadata saver. No other custom nodes needed.<hr /><h2 id="files-you-need-(in-manual-version)">📂 Files you need (in manual version)</h2><h2 id="ltx2.3-:">LTX2.3 :</h2>LTX2 Quant Model: <a target="_blank" rel="ugc" href="https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/main/models/diffusion_models/LTX-2/ltx-2.3-22b-dev.safetensors?download=true">base</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/main/models/diffusion_models/LTX-2/ltx-2.3-22b-dev-fp8.safetensors?download=true">fp8</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/main/models/diffusion_models/LTX-2/LTX-2.3-22B-Dev-Q8_0.gguf?download=true">Q8</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/main/models/diffusion_models/LTX-2/LTX-2.3-22B-Dev-Q6_K.gguf?download=true">Q6</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/main/models/diffusion_models/LTX-2/LTX-2.3-22B-Dev-Q5_K_S.gguf?download=true">Q5</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/main/models/diffusion_models/LTX-2/LTX-2.3-22B-Dev-Q4_K_S.gguf?download=true">Q4</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/main/models/diffusion_models/LTX-2/LTX-2.3-22B-Dev-Q3_K_S.gguf?download=true">Q3</a> In models/unetGEMMA-3: <a target="_blank" rel="ugc" href="https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/main/models/text_encoders/LTX-2/gemma_3_12B_it_fp4_mixed.safetensors?download=true">fp4</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/resolve/main/gemma-3-12b-it-Q8_0.gguf?download=true">Q8</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/resolve/main/gemma-3-12b-it-Q6_K.gguf?download=true">Q6</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/resolve/main/gemma-3-12b-it-Q5_K_S.gguf?download=true">Q5</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/resolve/main/gemma-3-12b-it-IQ4_XS.gguf?download=true">Q4</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/resolve/main/gemma-3-12b-it-Q3_K_S.gguf?download=true">Q3</a> in models/clipTEXT ENCODER: <a target="_blank" rel="ugc" href="https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/main/models/text_encoders/LTX-2/ltx-2.3_text_projection_bf16.safetensors">ltx-2.3_text_projection_bf16.safetensors</a> in models/clipVIDEO VAE: <a target="_blank" rel="ugc" href="https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/main/models/vae/LTX23_video_vae_bf16.safetensors?download=true">LTX23_video_vae_bf16.safetensors</a> in models/vae AUDIO VAE: <a target="_blank" rel="ugc" href="https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/main/models/vae/LTX23_audio_vae_bf16.safetensors?download=true">LTX23_audio_vae_bf16.safetensors</a> in models/vaeUpscale model: ltx-2.3-spatial-upscaler-x2-1.1.safetensorsin models/latent_upscale_models<h2 id="ltx2-:">LTX2 :</h2>LTX2 Quant Model: <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/LTX-2-GGUF/resolve/main/ltx-2-19b-dev-Q8_0.gguf?download=true">Q8</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/LTX-2-GGUF/resolve/main/ltx-2-19b-dev-Q6_K.gguf?download=true">Q6</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/LTX-2-GGUF/resolve/main/ltx-2-19b-dev-Q5_K_S.gguf?download=true">Q5</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/LTX-2-GGUF/resolve/main/ltx-2-19b-dev-Q4_K_S.gguf?download=true">Q4</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/LTX-2-GGUF/resolve/main/ltx-2-19b-dev-Q3_K_S.gguf?download=true">Q3</a> (i recommend Q5) In models/unetMelBandRoFormer : <a target="_blank" rel="ugc" href="https://huggingface.co/UmeAiRT/ComfyUI-Auto_installer/resolve/main/models/diffusion_models/MelBandRoFormer/MelBandRoformer_fp32.safetensors">MelBandRoformer_fp32.safetensors</a> in models/diffusion_modelsGEMMA-3: <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/resolve/main/gemma-3-12b-it-Q8_0.gguf?download=true">Q8</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/resolve/main/gemma-3-12b-it-Q6_K.gguf?download=true">Q6</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/resolve/main/gemma-3-12b-it-Q5_K_S.gguf?download=true">Q5</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/resolve/main/gemma-3-12b-it-IQ4_XS.gguf?download=true">Q4</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/resolve/main/gemma-3-12b-it-Q3_K_S.gguf?download=true">Q3</a> (i recommend Q4) in models/clipTEXT ENCODER: <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/text_encoders/ltx-2-19b-embeddings_connector_dev_bf16.safetensors">ltx-2-19b-embeddings_connector_dev_bf16.safetensors</a> in models/clipVIDEO VAE: <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/VAE/LTX2_video_vae_bf16.safetensors?download=true">TX2_video_vae_bf16.safetensors</a> in models/vae AUDIO VAE: <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/LTXV2_comfy/resolve/main/VAE/LTX2_audio_vae_bf16.safetensors?download=true">LTX2_audio_vae_bf16.safetensors</a> in models/vaeUpscale model: <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-spatial-upscaler-x2-1.0.safetensors">ltx-2-spatial-upscaler-x2-1.0.safetensors</a>in models/latent_upscale_modelsRecommanded LoRA:<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-distilled-lora-384.safetensors">ltx-2-19b-distilled-lora-384.safetensors</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Detailer/resolve/main/ltx-2-19b-ic-lora-detailer.safetensors">ltx-2-19b-ic-lora-detailer.safetensors</a></li></ul>in models/loras

【LTX2】TXT to VIDEO

🔄 Full Nodes 2.0 rewrite<ul><li>Rebuilt entirely with the UmeAiRT Toolkit pipeline (only 1 custom node needed)</li><li>SeedVR2 Upscaler and metadata saver now built-in with on/off toggles</li><li>12 nodes total — clean, visual, beginner-friendly</li><li>⚠️ Requires "Nodes V2 (Vue)" enabled in ComfyUI settings</li></ul>

Files with SHA256: d51d650a7fec98c96650acca7ed10cb2c58c37b47cc22f85e585cc1f6063f88b