Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
A GGUF version of the Image to Video workflow of the newest LTX Video version 2.3 in subversion 1.1.
Runtime profile
Source description
A GGUF version of the Image to Video workflow of the newest LTX Video version 2.3 in subversion 1.1.
Howto
Drag an image into the image nodes, adjust the prompt, and press queue. The rest should fit.
Description
An image to video ComfyUI workflow with LTX Video 2.3 subversion 1.1. The nodes are wired and visible in the traditional way and grouped together. No set and get nodes, no subgraph. I like it simple. It produces two videos, one with audio, one without.
Time
The example video in a resolution of 1024 x 576 was generated in 240 seconds at Windows 11 at an AMD Radeon AI PRO R9700. I have yet to test it on Linux, which is usually faster by a third.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
This ComfyUI workflow is for turning an image and a prompt into two videos—one with audio and one without. It is a GGUF workflow for LTX Video 2.3 version 1.1.
Its nodes are wired, visible, and grouped; it uses no set/get nodes or subgraph.
To use it, drag an image into the image nodes, adjust the prompt, and press queue.
Suggestion · not verified
Use it in ComfyUI with LTXV 2.3 as the base model.
Suggestion · not verified
The workflow was generated with 32 GB of VRAM.
Model files listed for this workflow include: gemma_3_12B_it_fp8_scaled.safetensors, ltx-2-19b-distilled-lora-384.safetensors, ltx-2-spatial-upscaler-x2-1.0.safetensors, ltx-2.3-22b-distilled-1.1-Q5_K_M.gguf, and ltx-2.3-22b-distilled-lora-dynamic_fro09_avg_rank_105_bf16.safett
Additional model files listed are: ltx-2.3-spatial-upscaler-x2-1.1.safetensors, LTX23_audio_vae_bf16.safetensors, taeltx2_3.safetensors, LTX23_video_vae_bf16.safetensors, and ltx-2.3_text_projection_bf16.safetensors.
Node packs listed for this workflow are: comfyui-custom-scripts, ComfyUI-GGUF, comfyui-kjnodes, comfyui-videohelpersuite, and rgthree-comfy.
For a lower-memory setup, try enabling the ram saver node.
Suggestion · not verified
The example video uses 1024 × 576 resolution.
Before use, verify that every named model file and node pack is available in your ComfyUI setup.
Suggestion · not verified
VAE decoding can be a bottleneck, and Linux use has not been tested.
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
3 excerptsSource context: 625 downloads · Type Workflows · Base model LTXV 2.3
Requirements
This workflow was generated with 32 gb vram. There is a ram saver node involved, which you can turn on. So you should be able to go lower. The bottleneck that even made my rig freeze is the VAE decode.
Estimated VRAM requirement
Estimate unavailable
20.4 GB across 3 of 8 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
13 requirementsText encoder · 12.3 GB · SAFETENSORS · Hugging Face · aleph65/comfyui
LoRA · 7.15 GB · Hugging Face · Lightricks/LTX-2
Upscaler · 950 MB · Hugging Face · Lightricks/LTX-2
ltx-2.3_text_projection_bf16.safetensors
Not resolvedText encoder · Unknown
ltx-2.3-22b-distilled-1.1-Q5_K_M.gguf
Not resolvedCheckpoint · Unknown
LTX23_audio_vae_bf16.safetensors
Not resolvedVAE · Hugging Face
LTX23_video_vae_bf16.safetensors
File unverifiedVAE · Hugging Face · LTX23 Video VAE Bf16.safetensors
VAE · Hugging Face · Karam98/tae-ltx2 · Tae Ltx2
Node pack · Registry
ComfyUI-GGUF
PossibleNode pack · Registry
Source context: 463 downloads · Type Workflows · Base model LTXV 2.3
Source context: 458 downloads · Type Workflows · Base model LTXV 2.3
Node pack · Registry
Node pack · Registry
Node pack · Registry
