SMOOTHMIX WAN 2.2 T2V v4.0 UPDATE! - 07/18/2026
For all the changes on the version please check the guide!
All videos made for the showcase of the model were made with the new Smooth Workflow v6.0 AIO.
SMOOTHMIX WAN 2.2 T2V v3.0 UPDATE! - 03/14/2026
Just tweaked the effects of the prompts "smoothmixanime" and "smoothmixrealism" and realism in general.
All videos on the High and Low Showcases were made using "WAN 2.2 Smooth Workflow v4.0" with settings: 900x600 resolution/Steps 8/Sampler Euler/Scheduler simple.
Just as T2V v2.0 it has light2xv baked in it.
The effects of the prompts "smoothmixanime" and "smoothmixrealism" were a little too strong - now you need to complement them with more prompts related to the visual style for the effect. Adding "Realistic Style" or "Anime Style" prompts should be enough. ^^
By popular demand (lol) you can make more normal sized breasts now - no flat chests thought, sorry flat chest lovers.
More details to skins if you try going for more realistic style videos - as long you don't use the "smoothmixrealism" prompt. In that case the skin will be very smooth automatically.
Added some Abstract concepts to it! It adds more variety and colors to the results.
GGUF MODELS For I2V v2.0 and T2V v2.0!
Great news for those that need GGUFs versions!
The user @BigDannyPt managed to convert SmoothMix WAN 2.2 Img2Vid v2.0 and SmoothMix WAN 2.2 Txt2Vid v2.0!!
Be sure to thank him for his efforts! =D
GGUF - SmoothMix WAN 2.2 Img2Vid v2.0
GGUF - SmoothMix WAN 2.2 Txt2Vid v2.0
SMOOTHMIX WAN 2.2 I2V v2.0 UPDATE!
For more info about the update and differences between versions check out this article.
All videos on the High and Low Showcases were made using "WAN 2.2 S. Workflow v2.0" with default settings except the resolution - they all used 900x600 on the workflow.
Lightx2v Lora is NOT merged this time so be sure to use pick any LoRA you prefer to accelerate generation as well as how much weight you use on them - all videos on the showcases used "lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16" set with weight 3.0 on High and 1.5 on Low.
To render futanari characters and male figures correctly, LoRAs remain essential. Try using mine or any of your favorites.
Be aware that hyper realistic content could possibly suffer some morphing since the model will gravitate towards the style of "SmoothMix Animations". That effect can be mitigated a bit by using Loras trained only on realistic content and by using prompts that pushes towards realism.
Sorry for the irregular posts and updates. I’m currently pretty busy and need to reorganize a lot of things, so free time has been scarce. If everything goes smoothly, I expect to have considerably more free time starting in February. Yay ^^
Have fun!
SMOOTHMIX WAN 2.2 T2V v2.0 UPDATE!
ITS FINALLY DONE! T_T
SmoothMix WAN 2.2 Txt2Vid v2.0 is what the model should have been in the first place - now it can show what can really be done!
Merged with Loras made with only images and videos generated from the SmoothMix Checkpoints!
Very high quality image and smooth animations! Use it with the updated version of the Smooth txt2vid Workflow in case you haven't downloaded yet!
Much - MUCH - more variety of clothes, hair styles, clothes, poses, body types and skins colors.
You can use captions or prompts! Both will work! Use both to ensure what you want is generated!
Fox girls, cat girls, demon girls, oni girls - all the girls (and MILFs) are here. ;)
It responds to the prompts 'SmoothMixAnime' and 'SmoothMixRealism'! All Loras merged to it had those key promtps from the SmoothMix Animations Style and they have the same effect here! Check the SmoothMix Animations Style page for details!
Its completely uncensored so it also should work MUCH better with NSFW Loras. Give it a try. ;)
IT CAN'T generate male anatomy reliably! You are going to need Loras for that! SmoothMix's priority is the ladies.
Smooth Mix Wan 2.2
A Smooth Mix version of the Wan 2.2 A14B!
I tried to make it as versatile as I could, I hope you guys like it!
Every video on the showcase used an image from my Gallery! All of them have a comment with a link to the source image used.
Key Points:
Every video on the showcase was made using my new Wan 2.2 Workflow v2.0/Txt2Video Workflow v.20 on its default settings. Make sure to use it!
No Loras were used to make the videos on the showcase. Try to make a video without using Loras first.
When using Loras, start by setting their weight between 0.3~0.5 and increase it if necessary.
Recommended Settings
Steps: 4 or 6
CFG: 1
Sampler/Scheduler: Euler a/Normal or UniPC/Simple
Resolutions:
Use the resolution that your Setup can handle. As a start I recommend these:
For HighEnd Spec PCs: 560 x 940 - 940 x 560
For Mid Spec PCs: 480 x 720 - 720 x 480
After testing these resolutions adjust as needed.
Have fun! =)
Description
FAQ
Comments (25)
Hi!
Do you plan to update the Image-to-Video model one day, or is that not something you're planning to work on? thanks !
I'm actually thinking of working on LTX right now. No plans for Wan 2.2 anymore.
Could you please add the int8 version？
I'll try when I get home. The process can take a long time so I can only do that by leaving the PC on all night. >.<
@DigitalPastel I'm really looking forward to the INT8 convrot version from you. It runs insanely fast at “crazy” resolutions on my mobile 3070. It feels like I upgraded my computer, but really, it's just that the technology has gotten better! Maybe you could try converting to int4 as well?
Great work. One of the best wan 2.2 checkpoints out there. One question. Can the models be converted into int8 by using silveroxides's script?
Sure. It should have no problems.
Actually let me clarify that the 4.0 model used the 'fp8_scaled' version of Wan 2.2 T2V. I'm not sure if using silveroxides's script would be beneficial.
It's beneficial if the model is converted from FP16 using the script.
@DigitalPastel yep. I just rechecked. It needs a bf16 model for conversion.
Will there be any updates to the I2V versions, we are still at 2.0 with them. I see we have a T2V 4.0 so just wanted to ask?
I'm actually thinking of working on LTX right now. No plans for Wan 2.2 for now.
Does the current 4.0 model support I2V? I tried using it in a workflow but it ignored the uploaded image that I had as the base for the I2V workflow. The model file name is labeled "smoothMixWan2214BI2V_t2vHighV40.safetensors" and "smoothMixWan2214BI2V_t2vLowV40.safetensors" so I am I missing something here?
wonder also with 2.0 what the latest workflow recommended is
4.0 is only Text to Video.
@snake88 using my latest workflow Smooth Workflow v6.0 AIO or any other with a I2V setup should work fine. Use the one you are comfortable with.
@serpentine18 Civtai atomatically renames the file when you download it - it's including I2V and T2V in the prexix because those are both part of this model family.
ko-fi link doesnt work just goes to home page?
I'll double check the link.
@DigitalPastel or just give us a wallet address and an email,we send the transaction id, u give us the download links, proton drive (why not just a wordpress + woocommerce website so we could buy it directly from u, takes about 4H top to set it up),
Could you tell me which Light2XV LoRA version was baked into your T2V v2, v3, and v4 models?
So you decided to ignore my comment. Good next time when u release an early access, I will buy it, make mirrors of it, and spam your model pages with direct download links. that will make you think twice and adjust your shitty behaviour toward us users. btw, why the F would you merge a goddamn UMT5 6gb into the i2v in both high and low noises? are those LoRAs truly yours or did you just leech them from HuggingFace?
These are extracted merged loras. if account get banned, I'll' be back with a new one.
High noise: https://drive.proton.me/urls/3ZJE31WB1M#nKGotqh30rtb
Low noise: https://drive.proton.me/urls/ACT4YMGESW#0KibhqRta8eD
Don’t use LightX2V LoRAs, already baked in with the extracted data. btw v4 is worse than v3 . At least in lora form you can control the strength. I’ll upload full checkpoints too, but it’s not really worth it.
This model is great. Maybe the closet thing we have to a pony t2v model. However, I'm having one major flaw on the majority of my creations. Maybe you can help me out or give me some prompt to prevent it from happening. That is, most girls look like they have balls in the doggystyle position. Maybe when you trained the futa and trans stuff into the model, it broke it a little bit. Some of the women have huge, fat areas down there and it almost hangs like balls. I'm not into that kind of thing so it kind of grosses me out when it happens.