update : April 14th 2026 : Lightricks has updated their LTX 2.3 distilled model to 1.1 (and Lora):Model (1.1 fp8 _scaled by Kijai): <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/diffusion_models">https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/diffusion_models</a>dist. Lora 1.1 : <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.3/tree/main">https://huggingface.co/Lightricks/LTX-2.3/tree/main</a><hr />V2.5 LTX-2.3 DEV &amp; Distilled Video with AudioImage to Video and a Text to Video workflow, both can use own Prompts or Ollama generated/enhanced prompts.<ul><li>works with latest LTX 2.3 Distilled model (8 steps, CFG=1) or Dev model (20 steps, CFG=3)</li><li>Updated the processing for DISTILLED and DEV model, select the DIST or DEV model in loader node and switch to dedicated DIST or DEV processing pipeline, so each model has its own processing.<ul><li>DIST model pipeline: Standard Guider and Basic Scheduler, follows the manual sigmas issued by Lightricks</li><li>DEV model pipeline: MultiModal Guider and LTX Scheduler + Distilled Lora on latent upscaler</li></ul></li><li>Included a workflow version with "RTX Video Super Resolution" node, which upscales videos in highspeed.</li></ul>Tip: With latest Comfy and LTX updates, the processing got faster for me, so I can increase the scale_by in sampler node from 0.5 to 0.6 or higher to have crisper videos with minor impact on render time.<hr />V2.3 LTX-2.3 DEV &amp; Distilled Video with AudioDownloads for LTX 2.3:<ul><li>LTX-2.3 Distilled &amp; Dev Models (fp8_scaled): <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/diffusion_models">https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/diffusion_models</a></li><li>Textencoder1: (fp8_e4m3fn, same as LTX-2): <a target="_blank" rel="ugc" href="https://huggingface.co/GitMylo/LTX-2-comfy_gemma_fp8_e4m3fn/tree/main">https://huggingface.co/GitMylo/LTX-2-comfy_gemma_fp8_e4m3fn/tree/main</a></li><li>Textencoder2: (projection_bf16): <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/text_encoders">https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/text_encoders</a></li><li>Video &amp; Audio Vae: <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/vae">https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/vae</a></li><li>Loras:<ul><li>Spartial upscaler (x2-1.1): <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.3/tree/main">https://huggingface.co/Lightricks/LTX-2.3/tree/main</a></li><li>Distilled Lora for upscaler (lora.384): <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.3/tree/main">https://huggingface.co/Lightricks/LTX-2.3/tree/main</a><ul><li>Smaller, alternative Desitilled Lora by Kijai: <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/loras">https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/loras</a></li></ul></li><li>Detailer Lora (same as LTX-2): <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Detailer/tree/main">https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Detailer/tree/main</a></li></ul></li><li>Ollama Model (prompt only, fast): <a target="_blank" rel="ugc" href="https://ollama.com/mirage335/Llama-3-NeuralDaredevil-8B-abliterated-virtuoso">https://ollama.com/mirage335/Llama-3-NeuralDaredevil-8B-abliterated-virtuoso</a><ul><li>alternative model with Vision (reads input image+prompt, slower): <a target="_blank" rel="ugc" href="https://ollama.com/huihui_ai/qwen3-vl-abliterated">https://ollama.com/huihui_ai/qwen3-vl-abliterated</a></li><li>other model with Vision (great for I2V): <a target="_blank" rel="ugc" href="https://ollama.com/huihui_ai/qwen3.5-abliterated">https://ollama.com/huihui_ai/qwen3.5-abliterated</a></li></ul></li></ul><hr />smaller LTX 2.3 GGUF Dev or Dist. models work as well. (replace Checkpoint loader node with Unet loader node from this custom node: <a target="_blank" rel="ugc" href="https://github.com/city96/ComfyUI-GGUF">https://github.com/city96/ComfyUI-GGUF</a> ):<ul><li>models: <a target="_blank" rel="ugc" href="https://huggingface.co/unsloth/LTX-2.3-GGUF/tree/main">https://huggingface.co/unsloth/LTX-2.3-GGUF/tree/main</a></li><li>save to models/unet/</li></ul><hr />V1.5 LTX-2 DEV Video with Audio including latest 🅛🅣🅧 Multimodal GuiderImage to Video and a Text to Video workflow, both can use own Prompts or Ollama generated/enhanced prompts.Replaced the Guider node with latest Multimodal Guider node, see more details in WF notes or here: <a target="_blank" rel="ugc" href="https://ltx.io/model/model-blog/ltx-2-better-control-for-real-workflows">https://ltx.io/model/model-blog/ltx-2-better-control-for-real-workflows </a>Before we had 1 CFG parameter for audio and video. With multimodal guider, we now can tweak audio and video seperately with even more parameters...<ul><li>added a Power Lora Loader node to inject further Loras</li><li>use Image to Video Adapter Lora to improve motion for I2V: <a target="_blank" rel="ugc" href="https://huggingface.co/MachineDelusions/LTX-2_Image2Video_Adapter_LoRa/tree/main">https://huggingface.co/MachineDelusions/LTX-2_Image2Video_Adapter_LoRa/tree/main</a></li><li>replaced a node to no longer require comfymath custom nodes</li></ul><hr />V1.0 LTX-2 DEV Video with Audio:Image to Video and a Text to Video workflow with own Prompts or Ollama generated/enhanced prompts.<ul><li>setup for the LTX2 Dev model.</li><li>uses Detailer Lora for better quality and LTX tiled VAE to avoid OOM and visual grids</li><li>2 pass rendering (motion+upscale). Upscale process uses distilled and spatial upscale Lora</li><li>setup with latest LTXVNormalizingSampler to increase video &amp; audio quality.</li><li>Text to Video can use dynamic prompts with wildcards.</li></ul><hr />Download LTX-2 Files: (Workflow V1.0 and V1.5 only)Find Model/Lora Loader nodes within Sampler Subgraph node.- LTX2 Dev Model (dev_Fp8): <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2/tree/main">https://huggingface.co/Lightricks/LTX-2/tree/main</a>- Detailer Lora: <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Detailer/tree/main">https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Detailer/tree/main</a>- Distilled (lora-384) &amp; Spatial upscaler Lora: <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2/tree/main">https://huggingface.co/Lightricks/LTX-2/tree/main</a>- VAE (already included in above dev_FP8 model, but needed if you go for GGUF models): <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2/tree/main/vae">https://huggingface.co/Lightricks/LTX-2/tree/main/vae</a>- Textencoder (fp8_e4m3fn): <a target="_blank" rel="ugc" href="https://huggingface.co/GitMylo/LTX-2-comfy_gemma_fp8_e4m3fn/tree/main">https://huggingface.co/GitMylo/LTX-2-comfy_gemma_fp8_e4m3fn/tree/main</a>- Image to Video Adapter Lora (more motion with I2V): <a target="_blank" rel="ugc" href="https://huggingface.co/MachineDelusions/LTX-2_Image2Video_Adapter_LoRa/tree/main">https://huggingface.co/MachineDelusions/LTX-2_Image2Video_Adapter_LoRa/tree/main</a><hr />Save Location:<ul><li>📂 ComfyUI/</li><li>├── 📂 models/</li><li>│ ├── 📂 checkpoints/</li><li>│ │ ├── ltx-2-19b-dev-fp8.safetensors</li><li>│ ├── 📂 text_encoders/</li><li>│ │ └── gemma_3_12B_it_fp8_e4m3fn.safetensors</li><li>│ ├── 📂 loras/</li><li>│ │ ├── ltx-2-19b-distilled-lora-384.safetensors</li><li>│ └── 📂 latent_upscale_models/</li><li>│ └── ltx-2-spatial-upscaler-x2-1.0.safetensors</li><li>│ └── 📂 Clip/</li><li>│ └── ltx-2.3_text_projection_bf16.safetensors</li></ul><hr />Custom Nodes used:<ul><li><a target="_blank" rel="ugc" href="https://github.com/Lightricks/ComfyUI-LTXVideo">https://github.com/Lightricks/ComfyUI-LTXVideo</a></li><li><a target="_blank" rel="ugc" href="https://github.com/rgthree/rgthree-comfy">https://github.com/rgthree/rgthree-comfy</a></li><li><a target="_blank" rel="ugc" href="https://github.com/yolain/ComfyUI-Easy-Use">https://github.com/yolain/ComfyUI-Easy-Use</a></li><li><a target="_blank" rel="ugc" href="https://github.com/stavsap/comfyui-ollama">https://github.com/stavsap/comfyui-ollama</a></li><li><a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-KJNodes">https://github.com/kijai/ComfyUI-KJNodes</a></li><li><a target="_blank" rel="ugc" href="https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI">https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI </a>(RTX VSR Version)</li><li>Text 2 Video only:</li><li><a target="_blank" rel="ugc" href="https://github.com/KoinnAI/ComfyUI-DynPromptSimplified">https://github.com/KoinnAI/ComfyUI-DynPromptSimplified</a></li></ul><hr />Ollama help:<ol><li>Install Ollama from <a target="_blank" rel="ugc" href="https://ollama.com/">https://ollama.com/</a></li><li>download a model: Go to a model page, chose a model , then hit the copy button, i.e. <a target="_blank" rel="ugc" href="https://ollama.com/huihui_ai/qwen3-vl-abliterated">https://ollama.com/huihui_ai/qwen3-vl-abliterated</a></li><li>open terminal and paste the model name, i.e.: ollama run huihui_ai/qwen3-vl-abliterated</li><li>model will be downloaded and can be selected in green comfy node "Ollama Connectivity". Hit "Reconnect" to refresh.</li></ol><hr />Example longer Video<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/YiRuWHLwVkI" start="0"></iframe></div><div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/6122l2tTKxc" start="0"></iframe></div>

LTX-2.3 DEV/DIST - IMAGE to Video and TEXT to Video with Ollama/RTX VSR

LTX-2.3 Text to Video and Image to Video with Ollama or own prompts Dev and Dist modelVersions with new RTX Video Super Resolution included

Files with SHA256: ae86fa2fae173328a46101c9bbd36caca63700d3215556cbbffee1b9d7552b75