Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
This is same as default WF in ComfyUI, but it uses GGUF custom node. Basically, you can insert images, audio, and video into any frame, so anything is possible.
Runtime profile
Source description
This is same as default WF in ComfyUI, but it uses GGUF custom node. Basically, you can insert images, audio, and video into any frame, so anything is possible.
T2V, S2V, V2V, I2V First, last, middle frame.
voice clone: You can input a few seconds of audio, and then crop those same few seconds after the process is complete.
reference image: input a starting image and then instruct it to perform a completely different action. (However, the character descriptions remain the same.) Yes, this is what's called a failed I2V. Again, crop the initial image.
extend video: input the images and audio extracted from the video. It will be extended for the remaining length.
GGUF custom node:
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use the LTX 2.3 basic GGUF 720p workflow (v1.0), based on LTXV2, to create or extend video from text, images, audio, or video and produce saved video output; it supports T2V, S2V, V2V, and I2V with first-, last-, or middle-frame images.
The workflow requires ltx-2-19b-distilled.safetensors and ltx-2-19b-lora-camera-control-dolly-left.safetensors.
Voice-clone use takes a few seconds of audio and can crop those same seconds after processing; reference-image use takes a starting image plus an instruction for a different action, can crop the starting image, and keeps the character descriptions the same.
For video extension, provide images and audio extracted from a source video; the workflow extends the remaining length.
Before use, update the GGUF custom node and ComfyUI to the latest versions.
Suggestion · not verified
Place text encoder-related files in ComfyUI\models\text_encoders, audio VAE files in ComfyUI\models\checkpoints, and the upscale model in ComfyUI\models\latent_upscale_models.
Suggestion · not verified
Listed ComfyUI nodes include LTXVConditioning, LTXVImgToVideoInplace, LTXVPreprocess, LTXVAddGuide, LTXVCropGuides, LTXVSeparateAVLatent, LTXVConcatAVLatent, LTXVEmptyLatentAudio, EmptyLTXVLatentVideo, LoadImage, LoadAudio, CreateVideo, SaveVideo, VAELoader, VAEDecode, VAEDecodeT
Other listed ComfyUI nodes include DualCLIPLoaderGGUF, UnetLoaderGGUF, LoraLoaderModelOnly, KSampler, KSamplerSelect, SamplerCustomAdvanced, LTXVScheduler, LTXVLatentUpsampler, LatentUpscaleModelLoader, ImageScale, ImageScaleBy, CFGGuider, RandomNoise, TorchCompileModel, and the.
Listed model files include google_gemma-3-12b-it-qat-Q6_K.gguf, ltx-2-19b-distilled.safetensors, ltx-2.3-22b-distilled-Q6_K.gguf, LTX23_video_vae_bf16.safetensors, ltx-2-19b-ic-lora-pose-control.safetensors, ltx-2-19b-lora-camera-control-dolly-left.safetensors, and ltx-2-spatial-
For T2V, set bypass image on; for I2V, set bypass image off.
Suggestion · not verified
Use the distilled model with distilled-embedding, or the dev model and dev-embedding with distilled-lora.
Suggestion · not verified
For low-resolution output, you can bypass the upscale node and start with a lower length, perhaps 9.
Suggestion · not verified
Before use, verify the listed node names and model filenames against what is installed in your ComfyUI setup.
Suggestion · not verified
With a reference image, review whether the generated action matches your intent; the character descriptions remain the same.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
3 excerptsSource context: 7269 downloads · Type Workflows · Base model LTXV2
( Please update your GGUF node and ComfyUI to the latest versions. )
LTX2.3 and other: https://huggingface.co/unsloth/LTX-2.3-GGUF/tree/main
or
upscale model: https://huggingface.co/Lightricks/LTX-2.3/tree/main
text encoder:
Place the text encoder-related files here: ComfyUI\models\text_encoders
audio vae is here: ComfyUI\models\checkpoints
upscale model is here: ComfyUI\models\latent_upscale_models
Use the distilled model and distilled-embedding, or use the dev model and dev-embedding with distilled-lora.
T2V: set bypass image on
I2V: set bypass image off
You can bypass upscale node for lowres.
Try starting with a lower length (perhaps 9).
Remaining hardware or download-size estimates are not available yet.
Requirements
google_gemma-3-12b-it-qat-Q6_K.gguf
Not resolvedText encoder · Unknown
VAE · 40.4 GB · Hugging Face · Lightricks/LTX-2
ltx-2-19b-ic-lora-pose-control.safetensors
Source context: 6808 downloads · Type Workflows · Base model LTXV2
Source context: 6535 downloads · Type Workflows · Base model LTXV2
LoRA · Unknown
ltx-2-19b-lora-camera-control-dolly-left.safetensors
File unverifiedLoRA · Hugging Face · Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Left · LTX 2 19b LoRA Camera Control Dolly Left
ltx-2-spatial-upscaler-x2-1.0.safetensors
File unverifiedUpscaler · Hugging Face · Lightricks/LTX-2 · LTX 2
ltx-2.3_text_projection_bf16.safetensors
Not resolvedText encoder · Unknown
Checkpoint · 16.6 GB · Hugging Face · unsloth/LTX-2.3-GGUF
LTX23_video_vae_bf16.safetensors
File unverifiedVAE · Unknown · LTX23 Video VAE Bf16.safetensors
