You can click on the link below and try it out directly. If the effect is good, you can deploy it locally.
Online Workflow: Wan2.2 Remix i2v 3.0 Image-to-Video Automatic Reverse
Experience link: https://www.runninghub.ai/post/2033536710499373058/?inviteCode=rh-v1325
Online Workflow: Wan2.2 Remix I2V v2.1 SVI2Pro Fully Automatic Reverse Long Video
Experience link: https://www.runninghub.ai/post/2008833586203463682/?inviteCode=rh-v1325
Online Workflow: Wan2.2-Remix-T2V-v2.0 text-to-video workflow
Experience here: https://www.runninghub.ai/post/1991533843182264322/?inviteCode=rh-v1325
Online Workflow: Wan2.2-Remix-I2V-Comfy-Qwen3
Experience here: https://www.runninghub.ai/post/1986632318448267265/?inviteCode=rh-v1325
Now! Register to get 1000 points, daily login 100 points, play 4090! Experience the super power of 48G!
[B-site video]: https://www.bilibili.com/video/BV1hF2cBNECZ
[Hugging Face: Wan2.2-Remix]:https://huggingface.co/FX-FeiHou/wan2.2-remix
[Telegram Group]: https://t.me/wan22remix
The workflow is very simple to use, and I have uploaded a tutorial on how to use it on YouTube. You can try it out and follow the tutorial and Civitai's workflow to easily reproduce the results. Thank you. If you have any other questions, please leave a comment in the comment section
Model Overview — Wan2.2-Remix
Wan2.2-Remix is a research and creative model built to generate short, cinematic video clips directly from text prompts. It focuses on human dynamics, realistic motion, and scene consistency, producing lifelike movement and smooth transitions without requiring LoRA setup.
This model already includes NSFW capabilities, enabling the generation of high-quality NSFW-themed videos without the need for additional LoRA.
High-noise model T2V: Lightx2v Wan2.2 Lightning dyno version (quantized to fp8)
High-noise model I2V: Comfy-Org Wan 2.2 ComfyUI Repackaged (fp16, quantized to fp8)
Low-noise model: Comfy-Org Wan 2.2 ComfyUI Repackaged (quantized to fp8)
Enhancements: Blended with open-source motion LoRA data and refined pose training for enhanced realism, anatomical precision, and gesture diversity.
Integration: Fully compatible with
lightx2v, no extra setup required.Recommended CLIP: NSFW-Wan-UMT5-XXL
Recommended Settings:
Steps: 4–8
CFG: 1
Shift: 5–10
Sampler: Euler
Scheduler: Simple
This release is currently beta. While functional, it is not yet perfect—feedback and testing are highly appreciated.
The GGUF version of the Remix model is now available.
Thanks to @BigDannyPt for creating it!
Download link:Wan2.2-Remix I2V GGUF v2.0
Changelog
I2V v3.0
Added VBVR LoRA to enhance spatial understanding and improve scene consistency.
Introduced UnifiedReward optimization to improve overall video quality and generation stability.
Adjusted several NSFW LoRAs to improve quality and visual consistency in NSFW scenes.
This version is considered the final release of the Remix I2V series.Unless there are major technological breakthroughs in the future, no further updates are planned.
I2V 2.1
Enhance facial consistency in long videos
Adjust LoRA ratio to make video dynamics more realistic
The v2.1 version has reduced the weight of the NSFW in the low-noise model to enhance character consistency. If you want to get a better NSFW, you can mix and match the low noise model of version 2.0.
T2V 2.0
Optimized character stability in generated videos, reducing jitter and unwanted motion artifacts
Enhanced video detail for more visually rich scenes
Added dynamic motion effects to improve realism and cinematic impact
Updated base model to original Wan2.2 version to minimize differences across random seeds
I2V 2.0
Significantly enhanced character motion and poses for more dynamic animations
Greatly improved camera movement and cinematic framing
Optimized NSFW content weighting to reduce jitter in generated videos when producing SFW scenes
Enhanced explosions and particle effects for more impactful visuals
SFW version will no longer receive updates
I2V 0.8
Updated lighting acceleration module to Wan2.1 version, fixing slow-motion character issues
Integrated over 20 open-source LoRAs and 10 custom-trained LoRAs to enhance motion dynamics
Removed several low-quality LoRAs to improve overall visual fidelity
T2V 1.0
Reduced dyno weighting to improve stability across different random seeds
Added more Asian facial datasets for greater diversity
Enhanced character motion dynamics for fluid animation
Improved motion amplitude, gesture diversity, and overall visual quality
T2V 0.9
High-noise T2V model: Lightx2v Wan2.2 Lightning dyno version (fp8)
High-noise I2V model: Comfy-Org Wan 2.2 ComfyUI Repackaged (fp16, fp8 quantized)
Low-noise model: Comfy-Org Wan 2.2 ComfyUI Repackaged
Refined character motion blending for smoother transitions
Enhanced anatomical articulation and natural body flow
This model incorporates the following Loras. Thank you to the Lora authors for their work. In order to facilitate management, I will change the file name uniformly after downloading Loras, so I cannot correspond to their real names one by one. Please understand. If there is any infringement, please contact me and the next version will remove it.
Wan2.1 - lightx2v_I2V_14B_480p_cfg_step_distill_rank256_bf16
Wan2.2 - I2V_A14b_high_noise_lora_rank64_lightx2v_4step_1022
Wan2.2 - I2V_A14b_low_noise_lora_rank64_lightx2v_4step_1022
Wan2.2 - Fun-A14B-InP-HIGH-MPS_resized_dynamic_avg_rank_21_bf16
Wan2.2 - Fun-A14B-nP-LOW-HPS2.1 resized dynamic avg rank 15 bf16
Wan2.1 - Skyreels-v2-T2V-720P LoRA rank64 fp16
Wan2.2 - PusaV1_lora_HIGH_resized_dynamic_avg_rank_98_bf16
Wan2.2 - PusaV1_lora_LOW_resized_dynamic_avg_rank_98_bf16
Wan2.1-T2V-BBFW - Better Buttholes For WANv1
Wan2.1-12V-General NSFW-Low
Wan2.2-12V-Hip Slammin Assertive Cowgirl
Wan2.2-12V-PENIS LORA e496
Wan2.2-12V-DR34ML4Y -All-In-One NSFW
Wan2.2-T2V-Body Shots v2 14B
Wan2.2-12V-Deepthroat, Blowjob
Wan2.2-T2V-Masturbating Rubbing 14B
Wan2.2-T2V-Doggy Style-14B -v3
Wan2.2-12V-COWGIRL+REVERSE COWGIRL-14b
Wan2.2-12V-Combo Handjob Blowiobsafetensors
Wan2.2-Bounce-Test
Wan2.2-T2V-GodPussy
Wan2.2-T2V-MysticXXX
My Train:
P001-Side-Lying-Sex-Wan2.2-i2v v10
P003-Sexy-Enhancer-Wan2.2-i2v
P004-Lying-Bouncing-Wan2.2-i2v v20
P005-Chinese-Dance-i2v-v20
P006-Squirting-Wan2.2-i2v
P008-Running-Wan2.2-i2v v10
P009-The-Walk-Wan2.2-i2v-Light
P010-whip-t2v-v10
F006-AsianGirls-Wan2.2-t2v v10Disclaimer
This model is released for research and creative purposes only. It must not be used for illegal, unethical, or harmful activities. The author assumes no responsibility for any misuse or consequences arising from its use.
Description
FAQ
Comments (43)
very few faces. makes almost all images and videos with one face.
The I2V version is dampening the motions of the other loras near zero. The 0.6 did this too but not that strong. Is it possible to fix that somehow? Is there a list of the baked in Loras, so i can maybe fix that with a clever prompt? I think some of the baked in loras doing this.
How do you add loras to your workflow?
Similar to this super fusion model, it is not recommended to add other loras it will degrade the video quality
When you want to use loras with this model, you can download one of my Videos. There should be emded a very simple and easy workflow.
First time doing video generation. I used your workflow and it took 37 minute to generate a 512x768 81 frame video.. and I got OOM error on 720p. I have a RTX 5080 15gb. Also running SageAttention.
are you running of bunch of stuff or playing video on the side? mine took like less than 4 mins with my 5070 Ti
@pakeru199 nope every background program is closed, only comfyui is running. are you using the workflow from downloading the video in the main post (T2V HighNoise v1.0)? If not what is your workflow?
recommended WF for I2v?
just download a video and the wf is in it
@joeflowetc622 Never felt so dumb lol
@Gooodis live and learn. i felt the same one time bro
Hi, the instructions say: 'Download the video and drag it into Comfyui to get prompt words and workflow'.
I downloaded the .mp4 file, but when I drag it into ComfyUI, nothing happens.
I want to use the 'Wan2.2-Remix (T2V&I2V)' model, but I can't find the specialized workflow. I'm a beginner and I'm pretty lost.
Can anyone tell me where to find the workflow?
oh i miss this plugin 'VideoHelperSuite(VHS)'
Of the custom T2V WAN models, this has been the best one I have used so far.
Your opinion on using this as base checkpoint to train lora?
If its a good idea to begin with, any plan to provide a file structure similar to https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B/tree/main so we can use it as base model with diffusion-pipe?
Suggest training Lora on the original model
Damn, I'm gonna be researching all night long!
T2V NSFW is the best variant of WAN2.2 that I saw.
Surprisely I found out T2V NSFW provides better result then SFW, more accurate and natural.
Thank you!!!
Will we see GGUF?
Honestly, I thought it was going to be good, so I downloaded everything and then checked that it's exactly the same as the base model. I don't think there's anything different about it. I ran some tests, and everything came out blurry, which isn't the case with the Dasiwa, for example...
so do i, i thought it was good its just a bit better than based wan, dasiwa just a lot or insanely better in every aspect
If you encounter any issues while using this Lora, you can use my workflow.
Online Workflow: Wan2.2-Remix-I2V-Comfy-Qwen3
Experience here: https://www.runninghub.ai/post/1986632318448267265/?inviteCode=rh-v1325
@FX_FeiHou Muchas gracias lo probaré
Wow. This checkpoint is a major advancement in nsfw technology. I just threw all my previous nsfw workflows, checkpoints and loras to the garbage and rebuilding everything around this one. This checkpoint replaces a dozen badly weighted, incompatible, lowres nsfw loras. Additionally, for the first time, my personal character lora retains near perfect identity over the boundary of 41-81 frames, currently running at 121 and the face still holding up. Allelujah. Sent 1k buzz tip. Note: at first I was downloading the sfw, then realized the nsfw version is accessible via the external link. Thank you.
No I2V NSFW Version? And you should do it as GGUF variant. Then u will get much more downloads... ;)
Very great job.
But for same prompt in T2V, the results from different seeds are too similar.
This workflow is absolutely solid! Quick and easy to use. I do have one question about adding your Loras to the workflow, I tried to add a lora loader and but through connecting the nodes it made the image distorted, i tested it first without the lora loader and it worked a treat. Is there a specific way to connect the Lora loader that im missing
I also cannot figure this out.
Because it has already added a lot of LoRA, you can try to reduce the intensity of the LoRA you added, starting from 0.2.
I'm new to ComfyUI and wan, how do I use this? I've tried a few different workflows but none seem to work. Does anyone have a recommended workflow for this? I see people saying "Wow this workflow is so great!!!" but... what workflow? is the workflow in the room with us? and, what does "just download a video the workflow is in it" mean?
It means - click video and save it to mp4 file, then drag this file and put in comfyui this file and you will have all the workflow with prompts from this file.
@flo11ok874 Tried that, doesn't seem to do anything
@funkerBlonga Then download workflow from author Huggingface - https://huggingface.co/FX-FeiHou/wan2.2-Remix/tree/main/workflow
@flo11ok874 tyvm
@flo11ok874I afraid none of the workflows seem to work for me. Is there a place I can learn more about how to use this workflow?
If you encounter any issues while using this Lora, you can use my workflow.
Online Workflow: Wan2.2-Remix-I2V-Comfy-Qwen3
Experience here: https://www.runninghub.ai/post/1986632318448267265/?inviteCode=rh-v1325
Gguf version available here👍🏻: https://civitai.com/models/2094656?modelVersionId=2372201
which version is it? i mean is it the v2?
Checkpoint works great, really easy to prompt without the need of external lora's. The only issue im having is with the changing of the face in I2V workflows.
Any suggestions on how to prevent it without killing the quality?
If you encounter any issues while using this Lora, you can use my workflow.
Online Workflow: Wan2.2-Remix-I2V-Comfy-Qwen3
Experience here: https://www.runninghub.ai/post/1986632318448267265/?inviteCode=rh-v1325
@FX_FeiHou Yes, with the workflow you shared. it works crazy good and does not change the face. Thank you
Details
Files
wan22RemixT2VI2V_i2vLownoiseV08.safetensors
Mirrors
Wan2.2_Remix_NSFW_i2v_14b_low_lighting_v0.8.safetensors
Wan2.2_Remix_NSFW_i2v_14b_low_lighting_v0.8.safetensors
Wan2.2_Remix_NSFW_i2v_14b_low_lighting_v0.8.safetensors
Wan2.2_Remix_NSFW_i2v_14b_low_lighting_v0.8.safetensors
Wan2.2_Remix_NSFW_i2v_14b_low_lighting_v0.8.safetensors
Wan2.2_Remix_NSFW_i2v_14b_low_lighting_v0.8.safetensors
Wan2.2_Remix_NSFW_i2v_14b_low_lighting_v0.8.safetensors
Wan2.2_Remix_NSFW_i2v_14b_low_lighting_v0.8.safetensors
Wan2.2_Remix_NSFW_i2v_14b_low_lighting_v0.8.safetensors
Wan2.2_Remix_NSFW_i2v_14b_low_lighting_v0.8.safetensors
Wan2.2_Remix_NSFW_i2v_14b_low_lighting_v0.8.safetensors