Important Notice
Optimized to work with the latest version of ComfyUI (v0.18.1 + Frontend 1.42.8).
Overview
This workflow uses Wan2.2 I2V together with SVI 2.0 PRO LoRA to generate long-form videos of 81 frames or more.
Instead of generating 81+ frames in a single pass, the video is created in multiple segments and then merged.
Compared to traditional extend/long workflows, this approach preserves motion information from the previous segment, resulting in much smoother transitions without noticeable seams.
Latest News (v1.7)
3-pass mode has been removed due to improved motion range achieved through updated recommended Lightx2v LoRA settings.
In the Extend group, you can now specify the Length for each chunk.
Please normally output at 24 FPS. If the result looks like fast-forward in some cases, try using 16 FPS instead.
(1.6) End Frame feature is now available!
You can specify an end frame for each chunk. This allows much finer control, especially over camera work.
Special thanks to Well-Made for updating the SVI node into a more powerful version.
Newly Implemented Feature
Prompt Enhancement via Ollama
Prompts are enhanced using an LLM, allowing for more detailed and structured motion descriptions.
You can also input prompts in Japanese (other languages are possible by adjusting the persona settings).
To use this feature, Ollama and an LLM model must be installed on your local PC.
Please note that I do not provide support for installing or configuring Ollama or LLM models.
Optional Features
Resume Mode
Allows you to continue generation not only from the first frame, but also from a previously generated video.
If something goes wrong partway through the process, you can save the generated segment and resume from that point without starting over.
Notes
This workflow is configured for the GGUF version, but fp8
andDistillversions can also be used by switching the model loader.Designed with 480p output in mind.
There are many variations of Lightx2v LoRA, and their suitability depends on the type of video you want to generate.
Acknowledgements
Special thanks to Kijai for providing the excellent LoRA models and custom nodes.
Description
The settings have been changed to allow for faster and more dynamic motion.
Ollama and regular versions are now available.
Slightly improved stability. Some bug fix. (2026.01.18)
FAQ
Comments (9)
Having issues where I get a blurry video when genning? I’m using the recommended setting but getting a lot of temporal drift.
Thank you for trying my workflow.
First, in lightx2v only mode, please try using the native lightx2v LoRA instead of the recommended Kijai's lightx2v LoRA.
Next, in 3-pass mode, bypass CFGZeroStar inside the ModelLoader, set lightx2v steps to 3, and set CFG to 3.0 or 3.5. This matches a typical SVI workflow configuration.
For testing, I generated around 100 different videos (including NSFW content), and I did not observe the issues you described.
For reference, here is my ComfyUI environment:
RTX 3090 + 64GB RAM
ComfyUI 0.9.2
Python 3.12.9
PyTorch 2.9.1 + cu130
Blurry videos also happen when you use a checkpoint that already has a lighting lora merged to it, and of top of that you put a lighting lora, so, try to avoid that.
USE lightx2v 1022 VERSION
This is the best SVI2 Workflow I have come Across, Under 20mins for a 15 -20 sec video with seamless transitions on an RTX 4090 and 128gb RAM.
Thank you for creating amazing videos using my workflow.
I’ve released v1.2.1, which fixes several bugs, so please feel free to give it a try.
@javawock7618 all thanks to you, this is a solid workflow. I just got the 1.2.1, testing it shortly
Wan22_PusaV1_lora_HIGH_resized_dynamic_avg_rank_98_bf16.safetensors
where ？
Please refer to this.
ComfyUI/
└─ models/
├─ unet/
│ ├─ Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf
│ └─ Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf
│
├─ text_encorders/
│ └─ umt5_xxl_fp16.safetensors
│
├─ vae/
│ └─ wan_2.1_vae_fp32.safetensors
│
└─ loras/
├─ SVI_v2_PRO_Wan2.2-I2V-A14B_HIGH_lora_rank_128_fp16.safetensors
├─ SVI_v2_PRO_Wan2.2-I2V-A14B_LOW_lora_rank_128_fp16.safetensors
├─ Wan22_PusaV1_lora_HIGH_resized_dynamic_avg_rank_98_bf16.safetensors (optional)
├─ Wan22_PusaV1_lora_LOW_resized_dynamic_avg_rank_98_bf16.safetensors (optional)
│
└─ lightx2v/ (optional subfolder)
├─ wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors
└─ wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors