<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/TlV72fg9skw" start="0"></iframe></div>☕ One coffee = one happy creator: <a target="_blank" rel="ugc" href="https://buymeacoffee.com/the_frizzy1">https://buymeacoffee.com/the_frizzy1</a><hr />Every LTX 2.5 mode in one workflow, picked from one dropdown. Text to video, image to video, first+last frame, pose control, and Lightricks' 12 VFX LoRAs: remove a person, day to night, add water, alpha matte, layout to render. Video comes out with sound.<h2 id="what-you-need">What you need</h2>✔ Custom nodes — None. Core ComfyUI only. ✔ ComfyUI version — 0.45.0 or newer (for the RelayVSR nodes). On 0.44 use the <code>v3.1.1</code> file in <code>source/</code>. ✔ VRAM — 12 GB — tested, not estimated ✔ System RAM — 16–19 GB peak ✔ Tested on — RTX 3060 12 GB · 32 GB RAM · ComfyUI 0.45.0 ✔ Licence — Workflow MIT · LTX 2.5 and the LoRAs: LTX-2.x Community Licence<h2 id="models-to-download">Models to download</h2>Click a file name to download it. Put it in the folder shown, inside <code>ComfyUI/models/</code>. Every loader in the workflow also carries its own link, so ComfyUI's missing-models panel gives you a Download button per file.Required — 8 files, about 39.7 GB<h3 id="diffusion_models">diffusion_models/</h3>File: ltx-2.5-22b-distilled-transformer-nvfp4.safetensors — 18.7 GB (12 GB (tested)) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-nvfp4.safetensors">https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-nvfp4.safetensors</a>Put it here: ComfyUI/models/diffusion_models/File: rt_detr_v4-x-hgnet_fp16.safetensors — 0.1 GB (Pose mode) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/SDPose/resolve/main/diffusion_models/rt_detr_v4-x-hgnet_fp16.safetensors">https://huggingface.co/Comfy-Org/SDPose/resolve/main/diffusion_models/rt_detr_v4-x-hgnet_fp16.safetensors</a>Put it here: ComfyUI/models/diffusion_models/<h3 id="text_encoders">text_encoders/</h3>File: gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors — 15.4 GB (all modes) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors">https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors</a>Put it here: ComfyUI/models/text_encoders/<h3 id="vae">vae/</h3>File: ltx-2.5-video-vae-bf16.safetensors — 1.5 GB (all modes) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors">https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors</a>Put it here: ComfyUI/models/vae/File: ltx-2.5-audio-vae-bf16.safetensors — 0.4 GB (all modes) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors">https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors</a>Put it here: ComfyUI/models/vae/<h3 id="latent_upscale_models">latent_upscale_models/</h3>File: ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors — 1.0 GB (T2V / I2V) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors">https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors</a>Put it here: ComfyUI/models/latent_upscale_models/<h3 id="loras">loras/</h3>File: ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors — 0.7 GB (Pose mode) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Union-Control/resolve/main/ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors">https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Union-Control/resolve/main/ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors</a>Put it here: ComfyUI/models/loras/<h3 id="checkpoints">checkpoints/</h3>File: sdpose_wholebody_fp16.safetensors — 1.9 GB (Pose mode) Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/SDPose/resolve/main/checkpoints/sdpose_wholebody_fp16.safetensors">https://huggingface.co/Comfy-Org/SDPose/resolve/main/checkpoints/sdpose_wholebody_fp16.safetensors</a>Put it here: ComfyUI/models/checkpoints/<blockquote>The LTX 2.5 files and every LoRA need Agree and access on their Lightricks page first, logged in to Hugging Face.</blockquote>VFX LoRAs — optional, download only the ones you use. All go in <code>loras/</code>.<ul><li>Clean Plate — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Clean-Plate/resolve/main/ltx-2.5-22b-ic-lora-clean-plate-1.0.safetensors">clean-plate-1.0</a>, 0.33 GB</li><li>Day To Night — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Day-To-Night/resolve/main/ltx-2.5-22b-ic-lora-day-to-night-0.9.safetensors">day-to-night-0.9</a>, 0.33 GB</li><li>Water Simulation — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Water-Simulation/resolve/main/ltx-2.5-22b-ic-lora-water-simulation-0.9.safetensors">water-simulation-0.9</a>, 0.91 GB</li><li>Deblur — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Deblur/resolve/main/ltx-2.5-22b-ic-lora-deblur-0.9.safetensors">deblur-0.9</a>, 0.91 GB</li><li>Decompression — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Decompression/resolve/main/ltx-2.5-22b-ic-lora-decompression-0.9.safetensors">decompression-0.9</a>, 0.91 GB</li><li>Colorization — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Colorization/resolve/main/ltx-2.5-22b-ic-lora-colorization-0.9.safetensors">colorization-0.9</a>, 0.91 GB</li><li>Alpha matte — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Alpha-Gen/resolve/main/ltx-2.5-22b-ic-lora-alpha-gen-0.9.safetensors">alpha-gen-0.9</a>, 1.31 GB</li><li>Restore — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Restore/resolve/main/ltx-2.5-22b-ic-lora-restore-1.0.safetensors">restore-1.0</a>, 1.71 GB</li><li>Refine Details — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Refine-Details/resolve/main/ltx-2.5-22b-ic-lora-refine-details-1.0.safetensors">refine-details-1.0</a>, 1.31 GB</li><li>Pixel upscaler x2 — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler/resolve/main/ltx-2.5-22b-ic-lora-pixel-spatial-upscaler-x2-1.0.safetensors">pixel-spatial-upscaler-x2-1.0</a>, 0.33 GB</li><li>Layout to Render — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Layout-To-Render/resolve/main/ltx-2.5-22b-ic-lora-layout-to-render-1.0.safetensors">layout-to-render-1.0</a>, 1.31 GB</li><li>Ingredients — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Ingredients/resolve/main/ltx-2.5-22b-ic-lora-ingredients-0.9.safetensors">ingredients-0.9</a>, 1.31 GB</li><li>Cinemagraph — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-LoRA-Cinemagraph/resolve/main/ltx-2.5-22b-lora-cinemagraph-0.9.safetensors">cinemagraph-0.9</a>, 0.20 GB</li><li>Slow motion — <a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5-22b-LoRA-Slow-Motion-Control/resolve/main/ltx-2.5-22b-lora-slow-motion-control-1.0.safetensors">slow-motion-control-1.0</a>, 0.65 GB</li></ul>RelayVSR x2 — only for the RelayVSR switch. Needs ComfyUI 0.45.0+.<h3 id="diffusion_models">diffusion_models/</h3>File: relayvsr_x2_lightx2v_int8_convrot.safetensors — 5.16 GB Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/RelayVSR/resolve/main/diffusion_models/relayvsr_x2_lightx2v_int8_convrot.safetensors">https://huggingface.co/Comfy-Org/RelayVSR/resolve/main/diffusion_models/relayvsr_x2_lightx2v_int8_convrot.safetensors</a>Put it here: ComfyUI/models/diffusion_models/<h3 id="vae">vae/</h3>File: relayvsr_flash_vae_x2_fp32.safetensors — 0.13 GB Download: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/RelayVSR/resolve/main/vae/relayvsr_flash_vae_x2_fp32.safetensors">https://huggingface.co/Comfy-Org/RelayVSR/resolve/main/vae/relayvsr_flash_vae_x2_fp32.safetensors</a>Put it here: ComfyUI/models/vae/<h2 id="modes">Modes</h2>One MODE dropdown, and each path only runs when you pick it:T2V · I2V (first frame) · First + last frame · Pose control (IC-LoRA Union) · VFX video to video (12 LoRAs) · Layout to Render · Ingredients · Cinemagraph · Slow motionTwo switches change speed and size: LTX x2 upscale (on by default) and RelayVSR x2 (off by default).<h2 id="speed-on-my-rtx-3060">Speed on my RTX 3060</h2>T2V, 4 s, Megapixels 0.5, models already loaded, a new seed per run:<ul><li>on (default) — off relayvsr x2, 960x512 result, 1:19 wall, 11.1 GB peak vram</li><li>off — off relayvsr x2, 480x256 result, 0:35 wall, 11.3 GB peak vram</li><li>off — on relayvsr x2, 960x512 result, 0:43 wall, 11.1 GB peak vram</li><li>on — on relayvsr x2, 1920x1024 result, 1:41 wall, 11.3 GB peak vram</li></ul>Peak VRAM barely changes with the switches: the loaded LTX model itself fills the 12 GB. The off switch buys time, not VRAM headroom.Every mode run once at 960x512, 4 s: T2V 1:43 · I2V 2:00 · First+last 2:32 · Pose 3:44 · Clean Plate 3:27 · Layout to Render 3:30 · Cinemagraph 1:49 · Slow motion 1:49.<h2 id="what-did-not-work">What did not work</h2><ul><li>Ingredients: 9 of 9 runs kept the reference sheet's panel grid instead of making one shot.</li><li>Decompression invents text, so don't put screen recordings through it.</li><li>Layout to Render needs the First frame. Without one you get grey clay back.</li><li>Slow motion: use speed 0.2. 0.05 was not slower.</li><li>Strength above 1 did not help Cinemagraph, Slow motion or Ingredients.</li></ul>Strengths I settled on: Clean Plate 1.2 and name the person if they are sitting in shot · Colorization 1.3, at 1.0 the colour is dull and fades · Day to Night 1.0 with people moving · Water 1.0 at 1280x704 · everything else 1.0.<h2 id="get-the-workflow">Get the workflow</h2><ul><li>GitHub: <a target="_blank" rel="ugc" href="https://github.com/Thefrizzy1/The_frizzy1-Workflows/tree/main/workflows/ltx/ltx-2.5-ultimate-12gb">https://github.com/Thefrizzy1/The_frizzy1-Workflows/tree/main/workflows/ltx/ltx-2.5-ultimate-12gb</a></li><li>Hugging Face mirror: <a target="_blank" rel="ugc" href="https://huggingface.co/The-frizzy1/The_frizzy1-Workflows/tree/main/workflows/ltx/ltx-2.5-ultimate-12gb">https://huggingface.co/The-frizzy1/The_frizzy1-Workflows/tree/main/workflows/ltx/ltx-2.5-ultimate-12gb</a></li></ul>More videos on this stuff: <a target="_blank" rel="ugc" href="https://www.youtube.com/playlist?list=PLQ3PcJNbU2Ls">https://www.youtube.com/playlist?list=PLQ3PcJNbU2Ls</a>

LTX 2.5 Ultimate 12GB — T2V/I2V/FFLF + Pose + 12 VFX LoRAs + RelayVSR x2

v3.2.0 adds the two switches on the main node: LTX x2 upscale (on by default, off is about 2x faster at half the size) and RelayVSR x2 (off by default, upscales the finished video of any mode). Needs ComfyUI 0.45.0+. The v3.1.1 file without switches is in <code>source/</code> for ComfyUI 0.44.

Files with SHA256: 44e1a4b14e01480a59cc21b17e00aade7222232d0779c09461a19f9eb3ca28fd