Update 2026-05-13: LTX 2.3 All-in-One v3.0 workflow published
VideoFlow LTX 2.3 distilled 1.1 All-in-One v3.0
New Features:
Text-to-Video Support with a pre-configured set of LoRAs for creating photorealistic videos.
Image-to-Video Support for both first and last frame.
Optional Audio Integration (audio-to-video) with the ability to extract voice from recordings (file or recorded clip) to remove background noise.
Consistent Character Voice through voice cloning with just a 5-second reference audio (file or recorded clip).
Video Filters for adjusting brightness, contrast, saturation, sharpness, blur, and enhancing edges and details.
Film grain for a cinematic or analog effect.
50fps Support via frame interpolation.
Improvements:
Now using LTX 2.3 distilled 1.1 resulting in better emotions, movements and audio.
Faster, less memory-intensive color correction.
More explanations and guidance integrated.
Fixes:
Audio and video are now always perfectly in sync.
Resolution input (video dimensions) for image-to-video generation now works properly.
Update 2026-04-14: LTX 2.3 I2V workflow updated
VideoFlow LTX 2.3 distilled I2V v2.0
VideoFlow 2.0 is here, bringing major performance upgrades, better quality, and more flexibility to your workflow.
Key Improvements:
Much Faster Generation: Thanks to improved samplers and schedulers, videos generate approx. twice as fast compared to Version 1.0.
Higher Quality Output: Despite the speed boost, image quality, audio quality, and prompt adherence have all been significantly improved.
Flexible Model Support: You can now freely choose between multiple model types:
Checkpoint
GGUF UNet
Diffusion model
Optimized for Low VRAM Systems: With GGUF support, VideoFlow now runs much more efficiently on systems with limited GPU memory.
Optional Sampler Preview: Disable the sampler preview to further reduce generation time.
Improved Usability: Additional guidance and hint texts help you get the most out of the workflow.
Update 2026-03-15: LTX 2.3 I2V workflow added
VideoFlow LTX 2.3 distilled I2V v1.0
This workflow provides an easy-to-use image-to-video solution for LTX 2.3, designed to work seamlessly with the distilled LoRA model. It focuses on high-quality, realistic output, with the first-stage scheduler's sigma values finely optimized for best performance.
Subgraphs are used to keep the main workflow streamlined and easy to navigate. A live preview is displayed during generation, allowing you to monitor progress and stop the process early if desired. Additionally, the first-stage video can be decoded for quick previewing. This feature lets you watch a lower-resolution version of the final video and cancel immediately if the result doesn’t meet expectations.
As the distilled LoRA already delivers impressive quality in the first stage, you can skip the second stage entirely if your hardware has limited performance. An optional color-correction node is included to compensate for LTX’s tendency to introduce subtle color and lighting shifts, ensuring consistent visual quality.
Update 2025-08-24: Wan 2.2 I2V workflow added
VideoFlow Wan 2.2 I2V v1.0
VideoFlow is now fully optimized for Wan 2.2. It supports resolutions from 480p up to 720p, with the option to upscale smoothly to 1440p at 32fps. The process is accelerated by integrating Lightning LoRA during the final two-thirds of the generation steps, ensuring faster results without compromising quality. Importantly, Lightning LoRA does not influence the initial generation steps, preserving natural and fluid movements throughout the video. SageAttention with Triton is supported but not required. Instructions on how to set up and use the workflow are included within the workflow itself.
VideoFlow Wan 2.1 I2V v1.0
This image-to-video workflow is designed to generate smooth, realistic videos at 32 fps with a strong emphasis on fast, high-resolution output. At least 16 GB of VRAM is recommended for optimal performance. For additional speed improvements, you may also install SageAttention and Triton, though these are optional.
It's fast 🚀!
Sample videos were rendered at 768 × 1152 resolution and 16 fps, consisting of 81 frames, each video taking about 6 minutes to generate. The upscaling and frame interpolation to 1536 × 2304 resolution and 32 fps took approximately another 6 minutes on an RTX 4080 with 16 GB VRAM. Lower resolutions render even faster.
Key configuration for the sample videos:
Video model: Wan2.1 SkyReels V2 I2V 14B 720P
LoRA: Lightx2v
Steps: 4
Sampler: dpmpp_sde_gpu
Scheduler: beta
💡Comprehensive usage details and instructions are provided within the workflow itself.
Sample images for input were created with my PhotoFlow workflow.
The download of the workflow contains all sample videos, including the input image with its own workflow, the initial generated video and its upscaled counterpart, allowing for convenient side-by-side comparison.
Leave a 👍 if you like the workflow 🙂.
Description
FAQ
Comments (12)
Default Upscaling is VERY silly. The same seed and settings produce the same result every time, so only when you get a MINIMUM time video (ie., 16FPS) you like should you upscale it, and then you can choose to use an 'expensive' upscaler.
PS it is also possible to have an upscale and interpolate only workflow, so you need not waste time rendering the original video again.
This is why all the steps are in groups, so you can mute the step and stop the generation whereever you want. If you would split it in two workflows, you would need to save all single frames everytime to have an uncompressed base for the upscaling. That's possible, but not my preference. I prefer to save disk space with the cost of a rerun of the initial generation of a video I Iike. With slow hardware, I would prefer the split. Feel free to split for yourself 🙂. Maybe I will add a save node for the frames and optional load from images for the upscaling. A rerun is not needed, if you want to upscale the last generated video. Just keep the seed, unmute the group and click Run and it continues directly with the upscaling.
I somehow run out of vram with this workflow even though i have 24GB and use the fp8 models.
# ComfyUI Error Report ## Error Details - **Node ID:** 3 - **Node Type:** KSampler - **Exception Type:** torch.OutOfMemoryError - **Exception Message:** Allocation on device This error means you ran out of memory on your GPU.
How can you run it with only 16gb vram as mentioned in the description?
edit: Ok nvm, using SageAttention fixed it, good workflow ;)
I don't have an explanation for it. Even if I deactivate SageAttention I don't run out of VRAM. I am happy you found a solution.
maybe the size of the output video ?
CharlieBrown0115 I didn't change the settings, just used the workflow out of the box
ai839 That is weird, the workflow also uses 23gb vram for me but that is probably because it uses more vram when more is available.
BubbleHash Maybe the Clip models stay in the VRAM if it fits together with the checkpoint. You used the fp8 models, right? Because the fp16 models need the 24 GB VRAM.
ai839 Yes, i used the fp8 models mentioned in the left info box
Omg, I am so in the mood for a burger, fries, and a hot redhead.
KSampler
No module named 'sageattention'
Read the info in the workflow in the top left info node. I explained that SageAttention is not installed by default. You can bypass the group, if you don't install SageAttention.