⚠️ Important information
All models already include the Lightning LoRAs, except the SVI models, where Lightning is not included.
Do not use additional Lightning LoRAs on models that already have Lightning integrated, or the quality will be degraded.
For SVI models, you can use Lightning LoRAs if you want faster video generation.
2or3 ksampler (for svi) https://civarchive.com/models/2079192?modelVersionId=2668801
v2.1 (for nsfw v2) https://civarchive.com/models/2079192?modelVersionId=2562360
v2.1 with MMAUDIO (for nsfw v2) by @huchukato https://civarchive.com/models/2320999?modelVersionId=2613591
Another wf triple KSampler KSampler https://civarchive.com/models/1866565/wan22-continuous-generation-svi2-pro-or-gguf-or-32-phase-or-upscaleinterpolate-w-subgraphs-and-bus?modelVersionId=2559451
triple KSampler wf setup allows for more motion and helps prevent slow-motion issues. In exchange, your videos will take longer to generate.
For those having issues with my SVI workflow , you can try Kijai's wf here: https://github.com/user-attachments/files/24364598/Wan.-.2.2.SVI.Pro.-.Loop.native.json. Alternatively, you can try fmlf wf https://github.com/wallen0322/ComfyUI-Wan22FMLF/tree/main/example_workflows they will be simpler. There are others on Civitai that work very well too.
Qwen-VL workflow as an alternative to Grok for creating your dynamic NSFW prompts. Thanks @huchukato for his work: https://civarchive.com/models/2320999?modelVersionId=2611094
🟣 SVI Update – NSFW
⚡ Model Presentation (SVI-compatible version)
This update was made because the NSFW V2 models were not fully compatible with SVI LoRAs.
This version was created to work smoothly with SVI, while still functioning without them (though the workflow must be adapted).
Be careful, SVI LoRAs will only work with a workflow specifically designed for them, otherwise, it won't work.
There are two models available for SVI:
✔ Fast Move (FM) – Sexual scenes may differ from the Consistent Face model and will generally be faster.
✔ Consistent Face (CF) – Slightly better image quality, which may be preferable for anime-style videos; sexual scenes differ from Fast Move, but the difference is minimal.
You can also mix models between High and Low LoRAs:
FM (Fast Move) as High + CF (Consistent Face) as Low
CF (Consistent Face) as High + FM (Fast Move) as Low
Both combinations work and give slightly different results, offering more flexibility for your videos.
For this version, the main improvements include:
✔ Fully adapted for SVI LoRAs
✔ Greater flexibility: Lightning and SVI LoRAs must be loaded manually for custom workflows
🟣 SVI LoRAs – Strengths & Weaknesses
⚡ Overview
✅ Strengths
Best solution for making long videos
Excellent transitions between video segments
Reduced degradation compared to other solutions
Strong character coherence: the model retains information from the previous video, helping maintain consistency
⚠️ Weaknesses
Weaker prompt understanding
Weaker camera understanding
Videos are less dynamic
Sometimes slow-motion effect
(can be improved with proper Lightning LoRAs, dynamic prompts or triple ksampler)
🟣 SVI LoRAs – Download Links
⚡ Download
Note: Both LoRAs must be loaded manually in your workflow.
🟣 Suggested Lightning LoRA Combos (Optional)
⚡ Overview
You don’t have to use these Lightning LoRA combos. They are optional and allow you to fine-tune motion and degradation.
You can also use other Lightning LoRAs or assign different combos per video for more control.
🔥 Combo 1 – More Motion (Rapid Video Degradation)
High LoRA →
https://huggingface.co/Kijai/WanVideo_comfy/blob/709844db75d2e15582cf204e9a0b5e12b23a35dd/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors
Weight: 4
or
💜 Combo 2 – Less Image Degradation
or
or
🟢 Combo 3 – Balanced Motion / Moderate Degradation
High LoRA →
https://huggingface.co/Kijai/WanVideo_comfy/blob/709844db75d2e15582cf204e9a0b5e12b23a35dd/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors
Weight: 3
Low LoRA →
https://huggingface.co/Kijai/WanVideo_comfy/blob/709844db75d2e15582cf204e9a0b5e12b23a35dd/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors
Weight: 1.5
🧠 Advanced Usage Tip
You can disable global Lightning LoRAs (in my wf) and assign different combos per video:
Combo 1 for Video 1, Combo 3 for Video 2, Combo 2 for Video 3.
Each combo produces different motion and degradation behavior.
If you want to create several-minute-long videos while maintaining high quality, it is possible, but it will take a very long time. You just need to avoid using Lightning LoRAs and use the full model instead.
🧠 Dynamic Prompts – Better Control & More Motion
You can use dynamic prompts to have better control and this helps to make the video more dynamic.
You just need to give this example prompt to an LLM like ChatGPT. It will be enough for it to describe the image you have and what you want as a video while keeping the same structure of the prompt in the following example.
⚠️ This will be a NSFW prompt; ChatGPT will not accept it.
You can use GROK https://grok.com, which can make NSFW prompt modifications.
For more examples of prompts with different poses, check:
Enhanced FP8 Model.
Give these prompts to GLM with the dynamic prompt structure if you want.
Example 1
(At 0 seconds: Wide shot showing a slightly overweight man casually walking down a city street, camera fixed in front, urban environment with buildings and cars.)
(At 1 second: Suddenly, a massive shark bursts from the pavement ahead, looking terrifying at first, pavement cracking, dust and debris flying, camera from side angle.)
(At 2 seconds: Medium shot from the side, the man stumbles backward in shock, while the shark dramatically slows down and strikes a comically exaggerated sexy pose, revealing large, exaggerated shark breasts, covered by a colorful bikini.)
(At 3 seconds: Close-up on the man’s face, eyes wide in disbelief, as he turns to look at the shark, small cartoon-style hearts floating above his head to emphasize his amazement, camera slightly low-angle.)
(At 4 seconds: Dynamic travelling shot showing the man frozen in the street, the shark maintaining its sexy pose, water splashes and debris still moving realistically, urban chaos around.)
(At 5 seconds: Wide cinematic shot pulling back, showing the man standing in the street, staring at the bikini-wearing shark with hearts above his head, epic perspective highlighting absurdity and humor.)
Example 2 – Anime NSFW
(At 0 seconds: The couple in a cozy bedroom, anime style, soft lighting highlighting their intimate embrace, her back arched slightly as he positions himself.)
(At 1 second: The man’s hips moving rhythmically, the head of his penis sliding effortlessly into her vagina, her body responding with a gentle, fluid motion, anime-style motion lines emphasizing the smooth penetration.)
(At 2 seconds: Her back arching deeply against him to intensify the pleasure, hips swaying with each thrust, breasts bouncing subtly, small hearts floating around them to capture the erotic energy.)
(At 3 seconds: Her face, eyes closed in bliss, a soft moan escaping, hands resting behind her head, anime-style blush on her cheeks, the air filled with a seductive aura.)
(At 4 seconds: The man penetrating her deeply, her body moving in sync with his, the bed sheets slightly rumpled, the room’s warm lighting enhancing the intimate, lustful atmosphere.)
(At 5 seconds: The couple locked in a passionate embrace, the scene exuding vibrant, seductive energy, anime style with smooth lines and soft shadows.)
🟣 Lightning Edition – NSFW I2V V2
⚡ Model Presentation (2 new versions available)
I originally planned to release only one V2, but some people preferred the NSFW V1 over the Fast Move V1 version, so depending on what you’re looking for, one version may suit you better than the other.
For these V2 versions, I tried a new approach:
✔ I made sure that most sexual poses work, while the model is also good for SFW content
✔ More flexible for general use
🔥 NSFW Fast Move V2
Improvements included in this version:
Better prompt understanding
Better camera understanding
Reduced unnecessary back-and-forth movements outside sexual poses
(cannot be completely removed, but strongly reduced)Improved bounce effect on the buttocks
If a man appears, he will no longer automatically attempt to penetrate the woman when she is nude
This version is designed for those who want more dynamic scenes with more movement.
💜 NSFW V2
The difference between this version and NSFW Fast Move V2:
Less camera control
Less camera understanding
But body movements are less pronounced (breasts and buttocks)
Some preferred V1 NSFW to V1 NSFW Fast Move, and this version keeps that spirit
For varied sexual poses, check the previews — there are many.
You can use the shown prompts and adapt them to your images, but of course, other prompts will work as well.
Don’t hesitate to use other LoRAs for creating specific concepts.
🔧 Recommended Settings
Steps: 2+2
(Jellai recommends 2+3 for even better results, and I agree)Sampler: Euler simple
CFG: 1
This model already includes the Lightning LoRAs, don’t use them, or the quality will be degraded
You need to download both models: H for High and L for Low.
Here is an example made with the base workflow + the First/Last Frame workflow + upscaler (only on the starting images) + inpainting (cum).
https://civarchive.com/images/114733916
🔞 LoRA Examples (with links and recommended weights)
LoRA: Penis Insert WAN 2.2
LoRA weight: 1
Face → Doggy
https://civarchive.com/images/112864483Face → Missionary
https://civarchive.com/images/112864718
https://civarchive.com/images/112864835Face → Doggy (leg aside)
https://civarchive.com/images/112864885Another example
https://civarchive.com/images/112864972
Other examples with different LoRAs
Face → Reverse Cowgirl — LoRA weight: 0.7
https://civarchive.com/images/112865189Face → Cowgirl — LoRA weight: 0.5
Face → Missionary — LoRA weight: 0.3
https://civarchive.com/images/112865381Face → Missionary — LoRA weight: 0.5
Face → Doggy leg aside — LoRA weight: 0.6
https://civarchive.com/images/112865551Face → Doggy — LoRA weight: 0.7
https://civarchive.com/images/112865696Face → Spoon — LoRA weight: 0.7
https://civarchive.com/images/112868124
Recommended LoRA to obtain a very realistic vagina and anus:
https://civarchive.com/models/2217653?modelVersionId=2496754
💡 Tip for Anime Style:
If you’re working in an anime style, feel free to follow the advice of @g1263495582 thanks to him for this.
Try these LoRAs together or separately; they help maintain face consistency:
🔹 Note:
For these LoRAs, use only Low Noise.
For the examples mentioned above, use High and Low Noise as indicated.
LoRA weight: 0.3
Many things can be done with the model, but don’t hesitate to use other LoRAs for specific purposes. And don’t hesitate to lower the LoRA strength to preserve the face as much as possible.
📷 Dynamic prompt example with different camera angles:
(at 0 seconds: wide shot showing the woman standing in the snowy plain, a massive giant dragon emerging behind her, snow cracking and dust rising).
(at 1 second: the woman jumps backward onto the dragon’s back as it bursts fully from the sky, camera tracking the motion from a side angle, debris and snow flying).
(at 2 seconds: medium shot from the side, the woman balances heroically on the dragon’s back as it begins to run forward across the snowy plain, slow-motion on her posture).
(at 3 seconds: close-up on the woman’s determined face, camera slightly low-angle to emphasize her heroic stance, snow and debris flying around).
(at 4 seconds: dynamic travelling shot alongside the dragon, showing the snowy plain, scattered debris and ice fragments flying everywhere as it gains speed).
(at 5 seconds: wide cinematic shot pulling back, showing the dragon taking off with the woman riding on its back, soaring above the snowy plain, epic perspective with snow, wind, and scale emphasizing the drama).
For available camera angles, check further down in the “cam V2” model description.
🔞 Normal Clip vs NSFW Clip:
You can also use the NSFW version for your clip.
It can bring positive effects for sexual scenes, but it can also cause issues, as in this example:
NSFW Clip:
https://civarchive.com/images/112864204Normal Clip (same seed):
https://civarchive.com/images/112864295
Here are the links to NSFW clips (thanks to zoot_allure855 for correcting the BF16 version):
BF16 fixed version:
https://huggingface.co/zootkitty/nsfw_wan_umt5-xxl_bf16_fixed/tree/mainFP8 version:
https://huggingface.co/NSFW-API/NSFW-Wan-UMT5-XXL/tree/main?not-for-all-audiences=true
❓ If you have any questions, don’t hesitate to ask!
Many people ask me for help via private message. You can do that, no problem, but I would appreciate it if you could do it in the comment section, it could help other people. Thank you.
🟣 Lightning Edition – NSFW I2V camera prompt adherence
⚡ Model Presentation (2 versions available)
I decided to release 2 versions. Both can produce different results, as you can see in the previews (the seed was the same).
Fast Move Version: provides more movement, and the movements will be faster, with better prompt understanding and camera handling
(you can see it in the 4th preview "fast move high" where the man slaps the woman)Natural Motion Version: offers more natural breast movements depending on the situation and produces slower scenes.
👉 Check both and choose the one that works best for you.
This NSFW edition is, of course, focused on sexual poses.
You should achieve very good results.
To create specific concepts, feel free to use specific LoRAs — they work very well with this model.
🔧 Recommended Settings
Steps: 2+2
(Jellai recommends 2+3 for even better results, and I agree)Sampler: Euler simple
CFG: 1
This model already includes the Lightning LoRAs, don’t use them, or the quality will be degraded
You can also use this T5, which may improve understanding:
https://huggingface.co/NSFW-API/NSFW-Wan-UMT5-XXL/tree/main?not-for-all-audiences=true
📝 Usage Tips
Start with a clean, high-resolution image for better results.
The model will not change the face; if it does, increase the resolution.
Also adjust your prompt if you are not getting what you want.
Wan understands some terms well, but not all.
For prompts, check the video previews: adapt them to your image.
Other prompts will work too.
🎥 Training
I trained 2 LoRAs:
The first one using several videos and images of different sexual positions.
The second one to bring more dynamic motion.
Respect to everyone who creates this type of LoRA — it requires a lot of work.
🙏 Credits
This model wouldn’t exist without the incredible work of these creators:
alcaitiff : https://civarchive.com/models/1295758/nsfw-fluxorwan-22orqwen-mystic-xxx?modelVersionId=2300332
Sweet_Pixeline : https://civarchive.com/models/1844313/penis-play-wan-22
anonimoose : https://civarchive.com/models/2008663/slop-twerk-wan-22-i2v
dtwr434 https://civarchive.com/models/1331682?modelVersionId=2098405
A special thanks to Alcaitiff and CubeyAI, two very kind and humble people.
🔔 Important
Please don’t support my work with buzzes here, I don’t need it.
If you want to support someone, support the creators listed above — they truly deserve it.
💬 Feedback
Feel free to give me feedback, positive or negative, to help improve future updates.
Update WAN 2.2 V2 CAM I2V – NEW feature Camera & Prompt Improvements
This custom version of WAN 2.2 I2V has been updated to deliver better prompt comprehension and improved handling of camera angles and cinematic movements. It provides more accurate scene interpretation, smoother transitions, and enhanced control over dynamic.
Key Features:
Excellent understanding of prompts and scene composition.
Supports various camera angles and movements, including zoom, dolly, pan, tilt, orbit, tracking, and handheld shots.
Ideal for cinematic storytelling, animated sequences, and creative video-to-image projects.
Flexible multi-step prompts, standard 4 steps (2+2), can be increased for higher fidelity.
Recommended sampler: Euler simple.
You can, of course, use your usual prompts; this is just one example among many.
Example Prompt with Different Camera Angles
(at 0 seconds: wide frontal shot of a man standing in front of an open fridge, cinematic lighting, subtle ambient kitchen reflections, the fridge contents visible, camera static).
(at 1 second: medium shot from the front as he opens the fridge fully, reaches for a can, slight zoom-in to emphasize the action, cinematic framing).
(at 2 seconds: camera shifts to a side medium shot, tracking him as he lifts the can to his mouth, fluid movement, maintaining lighting and reflections).
(at 3 seconds: camera starts a smooth 360-degree orbit around the man, following him as he drinks from the can, motion fluid, background slightly blurred for cinematic effect).
(at 4 seconds: close-up on his face and upper body while drinking, orbit continues subtly, fridge reflections accentuating realism, cinematic polish).
(at 5 seconds: final wide shot as he lowers the can, camera completes orbit to original angle, showcasing the kitchen space, lighting, and dynamic movement).
Available Camera Movements
Zoom / Dolly
zoom in
zoom out
camera zooms in on subject
camera zooms out gradually
dolly in
dolly out
camera dollies in slowly
camera dollies out steadily
crash zoom
Pan
pan left
pan right
camera pans across the scene
gentle pan left
sweeping pan right
Tilt
tilt up
tilt down
camera tilts up to reveal…
camera tilts down from…
Orbital / Tracking / Arc / Rotation
orbit around subject
360° orbit
camera circles around
tracking shot
camera tracks alongside subject
arc shot
curved camera movement
Other Movements & Styles
static camera / static shot
handheld shot
camera roll
Note:
LoRAs work perfectly with this model, offering full compatibility and consistent results across styles and concepts.
# SUPPLEMENTARY ADVICE
You can use negative prompts, but be careful: this will double the generation time.
Only use them if you really want to prevent something from appearing in your video.
In that case, enable the corresponding node; otherwise, keep it disabled.
⚠️ Important
The model must be used with CFG set to 1, so negative prompts do not work by default.
However, there is a simple way to enable them.
How to enable negative prompts:
Open the Manager
Search for kjnode and install it
In your workflow, add the WAN Nag node
To use it correctly:
Connect this node after the LoRA Loader
Feed it with the negative prompt
Then connect it to the first kSampler (High)
👉 Only use this option when necessary, to avoid unnecessarily increasing generation time.
And here is the negative prompt for unwanted movements:motion artifacts, animation artifacts, movement blur, motion distortion, dynamic distortion, shifting shapes, unstable render, instability, wobbling effect, jittering effect, vibrating render, inaccurate details, visual noise, distorted surfaces, rendering errors, warped shapes, exaggerated butt movement, jiggle, overanimated hips, unnatural butt motion, hyper bounce, extreme curves, distorted hips, unnatural pose, unrealistic anatomy, deformed body, disproportionate body, floating limbs, blurry textures, clipping, stretching, low detail, messy background, artifacts, butt bounce, moving hips, swinging hips, shaking butt, wiggling butt, moving lower body, moving pelvis, jiggling buttocks, bouncing butt, unstable stance, unnatural hip motion, exaggerated hip movement, hip sway, hip rotation, bottom motion, pelvis motion, wobbling hips, fidgeting lower body, dancing hips, pelvic movement, motion blur, unnatural movement
And here is the negative prompt from the official ComfyUI workflow:色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走
Note: If you use the default workflow without the node, this negative prompt will not work.
UPTDATE: Lightning Edition – T2V
I’m not really experienced with T2V myself, but a colleague who works with it a lot tested this version and confirmed that it performs very well. From the few tests I managed to do on my side, I got the same impression, although I haven’t compared it directly with the base version yet.
The settings are the same as in the image-to-video version: 2+2 steps or more if you prefer, CFG at 1, and Euler simple (though other samplers also work great).
I don’t plan to make an NSFW version for the T2V release,
but for the I2V version, I’m already quite happy with the first results.
Update WAN 2.2 V1.1 I2V
Updated version of the original Lightning merge — same settings 2+2 steps or more, featuring more movement and smoother flow (depending on the prompt).
The model already works very well in NSFW. Just use the right LoRAs, and the movement will improve.
WAN 2.2 V1 I2V
This checkpoint is based on the original WAN 2.2, with the Lightning WAN 2.2 and Lightning WAN 2.1 LoRAs already integrated. This improves image quality, makes motion smoother and more dynamic, and removes the slow-motion effect that can occur with the Lightning models.
A common setup is to use 2 steps on the high model and 2 steps on the low model, though other settings may work as well. Do not apply the Lightning LoRAs manually — they’re already included in this checkpoint.
My workflow
https://civarchive.com/models/2079192/wan-22-i2v-native-enhanced-lightning-edition
Description
FAQ
Comments (55)
Holy fuckin shit, my dumb ass has been trying to use this as a lora for like 2 days and wondering what the hell was happening
Many of the camera move commands I tried have absolutely no effect or have poor results. Practically only dolly or zoom works but nothing else from your list. NSFW Camera Fast version.
Hello and thank you for your feedback. The NSFW model does not have cameras as advanced as the V2 CAM model. The V2 NSFW version will have better cameras.
@taek75799 thank you. I will use that one for camera moves until the next one.
@kronos1959777 Alright, thanks for your reply. I hope you’ll like it. If I may, take a good look at the video previews on the CAM model, there are plenty of examples. Also look at the prompt structure; it could help you better control the WAN model. It’s also in the description.
@taek75799 actually i am trying the fp8 v2 version and camera moves don't work at all either. Maybe my version is out of date before the name was changed to add the NSFW in the filename? It is wan22EnhancedLightning_v2I2VFP8HIGH and 13.3 GB. maybe I should swap it with the one with the new name and see if that fixes it?
@kronos1959777 Honestly, it depends on the situation and especially on the seed. Sometimes you need to insist in the prompt and use the right words, but it doesn’t always work.
@kronos1959777 I don’t know why, but when I upload it, the name isn’t the same—Civitai changes it. This one is the correct one: wan22EnhancedNSFWCameraPrompt_v2CAMI2VFP8HIGH.safetensors.
Which camera are you looking for? I can try it and show you the result?
@taek75799 I think maybe I have duplicates. I have wan22EnhancedLightning_v2I2VFP8HIGH and wan22EnhancedNSFWCameraPrompt_v2CAMI2VFP8HIGH which are the same size files of 13,958,774 KB, and wan22EnhancedNSFWCameraPrompt_nsfwFASTMOVEFP8High and wan22EnhancedNSFWCameraPrompt_nsfwFP8High which are the same 13,958,824 KB
@kronos1959777 I don’t really know; it’s impossible for me to tell. I imagine Civitai changes the names for a good reason. FP8 files often have the same size or are very, very close. You would need to check the hash to be sure, but if you don’t know how to do that, it’s better to just download it.
@taek75799 I think it might have been because the photo reference i had was a person in front of a blank background wall, so maybe the AI couldn't motion track. A different photo worked.
@kronos1959777 Alright, thanks for your feedback. WAN is capable of doing many things, but there are also many situations where it struggles, or sometimes changing the prompt or seed can make it work.
Any Q8 version? these new models are suppose to have less bounces, right?
I've been testing for 3 hours now, it feels like the movements have become more realistic, there is no jelly anymore
@onelessreason515562 great news, then i guess i'm waiting for Q8 or at least Q6 version
Hello to you, I will release the Q6K in about 6 hours. For movements, it will be better in version 2 — at least I hope so; according to my tests, yes, but it’s really very difficult to test every situation.
Depends on how it was quantized
@taek75799 thx, is this Q6 going to be the V2?
@zereshkealt V2 will likely be released next weekend and will initially be in FP8.
"the people" thanks you for the gguf version :-)
Q4_KM... Guess I still have to buy some more RAM XD
(It okayish till I don't do anything else on my laptop)
Cheers & thanks again !
Hello and thank you for your reply, lol. I’m glad the people are satisfied. Have you ever tried Q3? Honestly, I’ve never tested it, so I don’t know if it actually degrades quality. You’re the second person who might need it.
@taek75799 I just switched my wan workflow from Q4 to Q3... (after a long conversation with this good pal GPT)
No more OOM (Fucking RAM...), best move ever (I thought It would be a downgrade... about prompt adhérence, about the output quality.... whatever... nope... On the contrary, I now can "multitask" during my renders, I can ask for more pixels and frames)
So... would you make a Q3 version ? Not for the people, just for me ? XD
Just joking, don't bother about it ... Just going to test your Q4 ... love your firsts outputs. Seems you didn't inject too much weird bouncing loras in your mix. Everybody love bounces, but we ve seen enough of crazy bouncing breasts (after 1000 hours of gameplay in a modded Skyrim, for example)
the natural swaying of this ass in your showcase makes me craving to test your toy ;-)
don 't know if your the 1rst to point it out, but I ve seen you were very aware of ..."the speed"
Seems to be a mystery with wan. I love my "low-motion" renders, but It s not always what I m asking for.
Seen on YT tuts that I should lower the HIGH lighting lora strenght....
BTW. no lighting loras to be used with your superb new models (?)
@BretChampagne If the Q4KM works, I recommend keeping it. The Q3 version is not recommended from what I’ve seen. And if FP8 works for you, keep FP8; it will be better than Q4. Later, if you really want the Q3 version, I can do it: I just need to launch the conversion and wait, but you won’t get the same quality.
For body balancing, it seems it’s not fully corrected yet, but in the next version I plan to release next week, it will be better, that’s for sure. After that, you just need to use a LoRA if someone wants balancing; I think that’s ideal.
For Lightning LoRAs, do not use them—they are included in the model. Thanks again for all your feedback, it really helps me.
Oh yes, I almost forgot one thing: there is a new node that allows better control of the so-called slow motions. Even if my model reduces them, it gives more control. It’s called Painter. Look at the end of the description, there’s a link to my WF where it is incorporated. But if you don’t want to use my WF, still take a look at it so you can incorporate it into your WF; it’s very easy, you just need to replace one node. Don’t hesitate to check the creator’s GitHub; he explains how it works.
glad i picked up 64gb b4 the price spike
@taek75799 Man, If you just helped me to resolve my "low-motion" issue, you will be my forever hero XD
About these versions issues, I have to disagree, Q3 gives me better results than Q4, cause I can generate higher res stuff. In the end the quality of my latest outputs has been higher...
Anyway... If I want I giant penguin entering the frame and slapping the girl s ass, I know I m better with standard WAN...
Very cool to speak with friendly guys as nerds as myself ;-)
@BretChampagne Lol, it’s true that the argument that they use fewer resources allows for increasing the resolution, I can only agree. So don’t hesitate to check the Painter node and look at my examples. In the V2 CAM version, there is no slow motion thanks to the cameras and the prompt structure; this could help you ;)
@taek75799 Thanks pal :-)
Can t wait to play with your CP...
... Still need a cool new idea as a start, as always ;-)
@taek75799 Thanks a lot for your time and each of your precious advices.
So... been playing with your cool NSFW toy for a few days now...
I love the way it fixes the low-motion issue we all have randomly with WAN 2.2 + lighting loras...
But I got back to standard WAN + loras XD
Sorry... your CP doesn't hurt faces too much, but I m very sensitive to it and the fact is (i ve read another "Civitayen" noticed that too...)
... That the model was turning every women in pornstars, so the faces get unwanted makeup, (but I could have lived with that), but the main problem is they are totally out of control (mouths wide open all the time, always bouncing bouncing bouncing - did you inject this legendary "NSFW experimental" into your work ? )
Tried the painter node (still playing with it right now), but I can't get to have a still cam, even on 1.15 motion amplitude (just wanted a natural motion, not a node taking film maker s initiatives), on a doggie action, this node wants to focus on the ass, even If I finetune my prompt...
Anyway... Thanks a lot. I ll probably post a few "over naughty bouncing pornstars" renders on this page very soon :-)
Hate to post even "half-negative" feedbacks to cool nsfw-ai-scientists like you...
Don t know how much time it took you to give "the people" this gguf CP ... CP alas, i probably won't use.
I could not do what you CP/loras creators do, I just don't have the patience. Most of people just want to play with your "toys" ... and eventually complain because it is was we do the best.
Hope my "feedback", not "complains" ;-) will help you to cook the best nsfw wan model of all times XD
My feeling is that creators shouldn't inject "nsfw exp lora" anymore in their new CP (to much bouncing)
I now add in low noise 0.7/0.8 a slop twerk lora, that does marvels about "natural" butt swaying, there are others slop bouncing breasts loras that do way better job than the nsfw experimental one.
Everybody love the "all in one Dreamlay", but it sucks at natural female body swaying...
Yep, even If I m not "creator", I know it all about "trial-and-error" and "fine-tuning" (not a garagist either...)
Cheers pal !
@BretChampagne Hello, don’t worry if the model doesn’t suit you, I understand. We don’t all have the same expectations. Regarding the body bouncing, you’re not the only one telling me this. I plan to release a V2 soon in which these bounces will be much less present. If I may suggest, try the V2 CAM version with some LoRAs just to see, or V1.1: they have no bouncing effect, no added NSFW, just camera optimization (V2) and better dynamics.
@taek75799 You are obviously a very cool guy. If I can get the "speed fix" that I have with your NSFW CP, without this bouncy craziness, i ll adopt your cam model for sure ;-)
BTW... Haven t you noticed the way this painter node tended to zoom in, even at low 1.15 motion amplitude (it s cool in its way, but I saw on YT tutorials that this camera should agitate at higher values)
@BretChampagne I did notice that as well, but I think I fixed it by setting the camera to fixed, I believe. But I'm not sure. Or maybe by changing the PainterI2V values.
@taek75799 You mean "fixed camera" in the prompt ? I tryed "still camera", "the camera remains focused on the girl s face" etc... This naughty cam couldn t help plunging into the girl s ass XD (would have done the same btw)
I ll post a few of these vids here very soon, promise ;-)
@BretChampagne Lol, the same thing has already happened to me too haha. But yes, it seems that with a fixed camera, or by adjusting the prompt, the problem disappeared.
Great model but I couldn't make a girl doing a fellatio to a BBC (I used multiple... descriptions).
Hello and thank you for your feedback, lol. It's something I haven't tried. The only advice I can give you is to add the BBC LoRA; it should work well. :)
@taek75799 kudos to you! I'll sure will, hehe!
q4km have quality loss vs fp8? Which one would you recommend for a RTX5080, 64gigs of ram?
Yes, FP8 is better than Q4KM. The equivalent of FP8 would be Q5. For you, the ideal would be Q8; it will be released this week. In a few hours, I will release Q6K, which is also a bit better than FP8.
@taek75799 Really? You don't need GGUF if you have a lot of free memory
@delta45424155 Q4K is smaller and there is a higher drop in quality, but since the model(s) have a lot of params and it saves a lot of memory, it's not so bad
@qek Thanks for your feedback. Personally, I have 16 GB of VRAM, and I use the Q8 version. It will be a few seconds slower compared to the FP8 version.
I'm experiencing a significant loss of image quality from the beginning of the video. What should I change to improve this quality?
Hello, you are using the high and low model correctly, right? Euler simple 2 + 2 steps? Do not use the Lightning LoRAs at all.
Don’t hesitate to download a preview video and drag it into your ComfyUI workflow; you will get all the correct settings.
@taek75799 muchas gracias probare, eso
@mediimedii1medii448 De nada, mi amigo.
thanks for adding the Q4 version. I'm still testing, but somehow I don't understand if I'm just writing poorly, even with the help of AI, or if I'm doing something wrong, oddities are happening - "corrupted" videos.
Hello, you are using the high and low model correctly, right? Euler simple 2 + 2 steps? Do not use the Lightning LoRAs at all.
Don’t hesitate to download a preview video and drag it into your ComfyUI workflow; you will get all the correct settings.
@taek75799 well, I meant that all sorts of AI things are happening, things that I would not like to see, like a penis turns into a vagina or vice versa (well, all sorts of creepy things). to be honest, I've done so much that I don't remember if I have an euler normal, and I also have lore enabled for 4 steps and yes 2 steps for high and 2 for low, I've tried 5 more.
I use fp8, very cool model, amazing quality, good prompt adherence in sex poses, NSFW has never been so easy, much better than the usual WAN with loras.
Thank you <3
Hello and thank you for your feedback, I’m glad you like the model.
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.