This is the SVI 2.0 PRO version.
v3.5 12-section fixed - An error was discovered where the prompt that should have been entered in "Section 8" was incorrectly duplicated with the 6th prompt. This issue has been fixed, so please reinstall the workflow.
Thank you so much to @MarcanOlsson for discovering the issue!
v3.5 12-Sec - This version is based on v3.5 and enables video merging through 12 generation steps.
When actually generating the video, you will notice color shifts compared to 6 generation steps. While 6 steps generally maintain better quality in practice, the ability to specify 12 steps offers advantages depending on the application, so we decided to add this version.
The 12-Section version enlarges the workflow, so unless you need more than 7 generation steps, I recommend using the standard v3.5.
v3.5 - The subgraph specification in the model input area has been deprecated and reverted to the v2 specification. Additionally, it is now possible to generate videos for only the first section.
We received multiple reports from the community that models such as CLIP and VAE were not functioning correctly due to the subgraph, and we also received feedback that the model placement was unclear. Therefore, we decided to revert to the v2 specification.
However, the subgraph of the generation section, which includes the sampler, remains unchanged. We believe that performing the generation process within the subgraph serves to prevent a decrease in generation quality. While the model area issue is simply a layout issue, the subgraph cannot be removed because it affects the quality of the generation section. If there are issues with the subgraph itself, please avoid using this workflow.
Regarding the video generation for only the first section, given the nature of SVI, we initially omitted it, believing that a single generation was unnecessary. However, we received feedback from the community requesting that a video be generated for each section, and that videos be added gradually while reviewing the generated videos. This was a very logical approach, so we added the "first video" and modified the workflow to allow videos to be accumulated while keeping the seed value fixed.
v3.4 - Layout adjustments.
v3.3 - Changed the seed node from "CR Seed" to "Seed (rgthree)". This change was made to align with commonly used custom nodes in this workflow, following reports of implementation issues with CR Seed.
v3.2 - Modified the layout to make it easier to disable Lightx2v Lora.
v3.1 - Modified the layout to make it easier to disable the Sage Attention node.
v3.0 released.
Video length can now be changed in each of the six generation sections, providing more flexible control over video content.
The frame rate (fps) was previously fixed at 16fps, but can now be changed arbitrarily. Accordingly, the RIFE-VFI node's scaling factor can now be changed in the input area.
GGUF model loader is now included as standard.
Version 2.0 changed the number of generation sections to six.
The layout has also been updated, allowing Seed node input to be processed in one place. Furthermore, the layout has been significantly redesigned to unify the user experience with Painter I2V versions, reducing the input burden. With this change, the wildcard prompt input method has been discontinued.
Please note that the explanations in this workflow are solely my personal opinions. I do not have expertise in AI generation, so some information may be inaccurate.
The main goal of this workflow is to achieve compact operation when performing repeated generation. It minimizes screen scrolling during operations such as prompt input, input image selection, specifying time, number of steps, resolution, and, most importantly, LORA selection. To further enhance compactness, all nodes are fixed to prevent accidental operation.
Links to the Models and LORAs and nodes used in this workflow
SVI LORA :
Wan Advanced I2V (Ultimate) :
https://github.com/wallen0322/ComfyUI-Wan22FMLF
This node was updated on January 27th, but the version available for installation from ComfyUI Manager may be an older version. While the older version will still work, you won't be able to set "SVI Motion Strength," and you'll likely experience more color misalignment. Therefore, if you can Git clone, we recommend installing the latest version.
Links to the Basic models of the Wan2.2
CLIP:
https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/text_encoders
VAE:
https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/vae
CLIP Vision :
https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/clip_vision
You can generate up to six generations, and each generation is assigned a unique seed value. Normally, click "Randomize Every Time" to display "-1". Generation will be random. In this case, the seed value for each generation will be displayed at the bottom of the screen. If you want to fix the seed value, click the seed value field or enter the seed value directly. For example, you can fix the first and second generations and regenerate the third generation and beyond randomly. However, regenerating a section before the generation section you want to fix will change the final frame, so you cannot fix subsequent sections. As a general rule, regenerate after the section you want to fix.
By combining the six generated videos, you can create six different types of movement. For example, by generating and combining six videos of different durations, you can create a long video containing six complex movements. This is one of SVI's strengths, enabling complex processing that is impossible with a single generation.
However, SVI V2.0 PRO also has its drawbacks. Because SVI uses the first image as a reference point, the AI tries to restrict movements that deviate significantly from the reference point. As a result, the movement becomes sluggish and unnatural. Furthermore, this constraint imposed by the reference point also reduces the responsiveness to prompts.
In short, the use of excellent LORA is essential in SVI. In my experience, movements without LORA are very unnatural, lack impact, and resemble something out of a horror movie. Fortunately, there are many excellent adult-oriented motion LORAs available. However, if you want to create completely original movements, expect it to be difficult with the current version of SVI.
I hope this workflow helps make video production with SVI more enjoyable.
Description
v1.3 - Fixed some minor bugs. Workflow structure remains unchanged.
since I have no knowledge of AI generation, these are merely my opinions, so please understand that they may contain incorrect information.
FAQ
Comments (13)
Thank you kind sir. May you be blessed. :)
Thank you for uploading the workflow, it is very helpful for me.
Thank you for your post.
What do you think is the difference between SVI and PLV?
I'd like to know the advantages and disadvantages of each.
Excuse me, what does PLV stand for?
@kenpechi He's asking about Painter Long Video (PLV)
Thank you for letting me know. Unfortunately, I don't even know the name of PLV, and I've never used it, so I can't really explain anything. I'm sorry.
kenpechi's work is incredible. I love all of it.
I'm having some ghosting problems with both the SVI and Painter workflows. Has anyone had something similar happen? It only comes up when I try to join two videos- it's fine if it's just one
Thank you for always watching my videos.
I'm not sure if this applies to your case, but the v1030 on the HIGH side of the Lightx2v LORA I use has quite a few quirks and sometimes causes ghosting. I don't get any ghosting with the v1022, but it's a bit more subdued, so I don't use it much. Also, with the v1030, if the action instructed by the prompt is a leap for the AI, the AI may try to forcefully follow the instructions, causing ghosting.
However, I rarely get ghosting these days, so it's difficult to pinpoint the cause.
@kenpechi Thank you for your reply! I think the problem is in merging both videos. I'll keep looking for the cause.
Hi, Great workflow, My question is what model and loras do you use to generate first image? I must say the clothes and outfit are amazing, no matter what prompt I give, I can't get the woman to have a pulled up bra. Can you help?
（Diving IL Real Asian）
https://civitai.com/models/1562047/diving-illustrious-real-asian?modelVersionId=2490435
（Wai Realism IL）
https://civitai.com/models/2233797/wai-realism-illustrious?modelVersionId=2514670
Recently, I've been using these two checkpoints in Illustrious. I only use LORA, which is related to image quality. For more details, please see the several posts in the images on my profile.
Is your question about the clothing not coming out as you expect in the generated images?
First of all, I use Illustrious, but it's completely different from using Flux or Z-image. I use prompts that are completely specific to Illustrious, so I have no idea about other models.
The state of the clothing in my images is 100% due to the prompts. I don't use any clothing-related LORA. So all I can say is that you should be more creative with your prompts, but if you're using something other than Illustrious, please understand that I won't be able to tell you.
@kenpechi Hey Thanks for the quick reply, the thing is I use Grok for prompt and clothing, I guess it's the model like Flux and ZIT that doesn't adhere unless you use loras with them, But for illustraious, I had no experiance, but I'm gonna give it a try and dive deep, cuz your photos are really good when it comes to clotheing I must say, :D
@jzaamir I hope it works out. Thank you for always watching my videos.