LoRA Overview｜Anime Cumshot Aesthetics – Precision Load
Anime Cumshot Aesthetics – Precision Load is a LoRA specifically trained to enhance the visual and stylistic quality of cumshots in anime-style videos, focusing on density, precision, impact, and aesthetic realism.
This model was developed to complement existing cumshot LoRAs like WAN CUMSHOT by focusing specifically on anime-style aesthetics and short-form timing. While general-purpose models aim for broad adaptability, Anime Cumshot Aesthetics – Precision Load targets refined features such as thickness, directional accuracy, and artistic expression, delivering paste-like cumshots with strong visual impact in tightly timed scenes.
All my video templates are upscaled, smoothed, and interpolated using my V2V (video-to-video) workflow.
About this version 2025/06/23 {UPDATE}
🎞 WAN 2.1 Anime Cumshot – Emotion Edition (LoRA)
🧠 Description
Anime Cumshot – Emotion Edition is a specialized LoRA built upon Anime Cumshot Aesthetics – Precision Load.
This version adds expressive facial and physical reactions during cum scenes, delivering dynamic and emotionally charged outputs that reflect anime-style shock, anger, acceptance, and more.
All my video templates are upscaled, smoothed, and interpolated using my V2V (video-to-video) workflow.
Wan v2v with Upscaling and Smoothing and Interpolation 放大平滑處理 - v1.03 use this version | Wan Video 14B i2v 480p Upscaler | Civitai
📁 Training Details
Clips: 33 original animated clips
Length: 3 seconds per clip
FPS: 16
Style: 100% anime
Trained Reactions: Facial expressions, blinking, flinching, head movement, eye tracking
LoRA Type: Emotion-focused enhancement
✅ Compatibility Notes and Personal Tips
This LoRA is designed primarily for anime-style scenes, but also works reasonably well in semi-realistic settings.
If you are working with realistic characters or lighting, I recommend pairing it with WAN CUMSHOT to achieve more natural pacing and impact.
Wan Cumshot - I2V v1.0 | Wan Video 14B i2v 480p LoRA | Civitai
In my experience, combining with leads to smoother results, especially in timing and shot rhythm.Emotion = 1.0 WAN CUMSHOT = 0.2~0.5 (You can try different weights, but try not to exceed my LORA's range.)
You can also use this LoRA alone without any problems in anime-style compositions. However, depending on your base model and prompt structure, some users may notice that the ejaculation and reaction timing may appear slightly slow or delayed.
This is a subjective issue I’m still investigating — I haven’t found a reliable method to speed up perceived motion yet.
🧪 Suggested Settings
Steps: 20 (You can try increasing the steps. Sometimes I use 22 to 24.)
CFG Scale: 6 (If you want your image to adhere more closely to your prompt, try increasing the CFG. Sometimes I use 6.2)
Sampler: UNI_PC
Scheduler: SIMPLE
🎯 Supported Emotional Reactions
😲 Surprise
・Eye-widening, shocked expression
・Visual Cue: flinch + wide eyes
😧 Disbelief
・Slightly open mouth, frozen/stunned expression
・Visual Cue: disbelief + open mouth
😐 Calm / Still
・Blank face, slow blinking, little to no reaction
・Visual Cue: slow blink + still face
😠 Anger
・Glaring, clenched jaw, tense expression
・Visual Cue: glare + clenched jaw
😊 Soft Smile
・Relaxed gaze, faint smile, subtle head lift
・Visual Cue: soft smile + head tilt
😒 Displeasure
・Subtle frown, quiet rejection or visible discomfort
・Visual Cue: frown + slight recoil
✔️ Additional Supported Reactions:
・Head tilt (slight up/down)
・Turning head (left/right)
・Eye closure / eye tracking
・Subtle recoil / delayed reactions
⚠️ Current Limitations (Work in Progress)
Prompt Compatibility: Works best with fixed, tested prompts. Varying wording might reduce stability.
Blended Emotions (e.g., shock → smile) are not yet stable.
Intensity Control: No fine control over light vs. intense emotions yet. All output is medium strength.
Limited Targeting: Does not yet support fine-tuned cum landing (e.g., thigh-only, chest-only).
💡 Recommended Pairing (if needed)
Anime Cumshot Emotion: 1.0WAN CUMSHOT: 0.3Wan Cumshot - I2V v1.0 | Wan Video 14B i2v 480p LoRA | Civitai
I have not tested compatibility with other LoRAsThis LORA can be used completely standalone without any issues, or you can try mixing it with other LORAs.
I've tried to improve the angles, but I haven't been able to solve very unique angles yet. You can try using it for specific body parts, which I also haven't figured out a solution for yet. For example, scenes focusing only on ejaculating on breasts or on buttocks.
I've tried a lot of source material, but haven't found a good solution. The only way might be to extract frames from videos and focus only on material of breasts or buttocks. I haven't tried that yet, but I'll give it a shot when I have time.
PROMPT:
Mix and match as desired. However, success isn't guaranteed, so please try it yourself or refer to my video examples.
A girl is kneeling
A girl is sitting.
A girl is standing.
A girl is lying down. If you want the man to not be in the frame at the beginning and then enter the frame from off-screen, use this.
A man's lower body and penis enter the frame from below.
A man's lower body and penis enter the frame from the right side.
A man's lower body and penis enter the frame from the left side.Main actions and landing points
The man is stroking his penis. He ejaculates on her face, in her hair, on her chest, into her mouth, on her tongue, stomach,If you want the woman to help the man, use this. For other scenarios where the woman helps the man, like using her breasts, I apologize, but I don't have that material. However, you can try it; theoretically, the ejaculating action shouldn't disappear.
She strokes his penis.Describe the state of the semen （Please use this as a reference to capture a similar feel）
The cum is thick and sticky, clinging like paste before sliding off.
The cum is thick and sticky, sticking to her skin before dripping down slowly.
The cum is thick and gooey, clinging to her lips and tongue before dripping off.
The sticky fluid briefly clings before slowly sliding off her skin.
It is thick and sticky, clinging like paste before sliding off slowly.
The sticky fluid clings briefly before slowly sliding off her skin.
The cum is thick and viscous, sticking tightly before sliding down her body.
Thick and heavy, the cum holds to her body before dripping away.
Emotion：
Here are all my available packages for your reference. You're welcome to mix and match, but I haven't tested too many combinations for success, so please try it yourself!
Her face shifts in an instant. She looks shocked, then tilts her head upward, staring toward the source of the cum.
A sudden jolt crosses her face. She flinches in shock, slightly recoiling as she slightly turns her head to the right.
She reacts immediately. Her eyes widen in shock, then she turns toward the source of the cum, looking very angry.
There is an instant shift in her expression. She flinches in shock, her eyes wide with disbelief.
She blinks slowly, without changing her expression.
A wave of shock washes over her face. She flinches in shock, slightly recoiling.
A sudden emotional shift appears on her face. She looks shocked, then turns toward the source of the cum, looking very angry.
A sudden change crosses her face. She flinches in shock, her eyes wide with disbelief.
There is a subtle shift in her expression. She blinks slowly, frowning faintly, her expression calm but clearly displeased.
A moment of disbelief flashes across her face. She looks incredulous, then tilts her head upward, staring toward the source of the cum.
Her expression remains unchanged.
Her face tenses briefly. She tilts her head upward, eyes following the source of the cum.
A quiet reaction passes over her face. She closes her eyes for a moment, frowning faintly. Her lips press together tightly, her face calm yet clearly displeased.
A quick flash of shock crosses her face. She flinches in surprise, her eyes wide with disbelief.
Initially, she is momentarily stunned. Then, flinching in shock, her eyes squeeze shut, and she instinctively recoils, noticeably turning her head to the right.
Her expression changes instantly. She furrows her brow, her mouth agape in disbelief and rage. She then looks up and glares toward the source of the cum, clearly furious.
As the fluid hits, she flinches in surprise, blinking a few times, then noticeably turns her head to the right.
A sudden wave of emotion strikes her face. She flinches in shock, her eyes wide with disbelief.
Her face is flushed. She stares ahead with hazy eyes, seemingly dazed yet still conscious, her expression calm and unresisting. Her left eye had briefly closed before reopening.
Her features soften. She smiles faintly and keeps her gaze on his penis without looking away.
Her brows twitch faintly. She closes her eyes for a moment, then reopens them with a slight smile.
A flash of shock flickers across her face. She flinches, her eyes wide with disbelief.
Her expression shifts suddenly. She flinches, then turns toward the source of the cum, her eyes wide with disbelief.
Her features soften slightly. With a soft smile, she lifts her head and looks up at him, letting the cum splash across her face and chest.
A sharp reaction crosses her face. She flinches in shock, her eyes wide open, then turns toward the source of the cum.
Her expression remains unchanged, her eyes simply closing.
She shifts her head slightly and watches him quietly, expression calm but aware.
A quiet disapproval flickers across her face. She blinks slowly, frowning faintly, then raises her head, her expression calm but clearly displeased.
As the fluid hits, her eyes widen in shock, and her mouth slightly opens, as she noticeably turns her head to the left.I usually put these supporting prompts below the main prompts I've written. This is a personal habit I find useful; you can decide if you want to use them yourself.
White translucent cum.
anime style, open eyes, eyelids match skin tone, Natural eyelids, anime eyelashes, simple eyelashesHere are my negative prompts for your reference.
blurry, out of focus, low detail, bad anatomy, ugly, overexposed, underexposed, distorted face, extra limbs, cartoonish, 3d render artifacts, duplicate people, unnatural lighting, bad composition, missing shadows, low resolution, poorly textured, glitch, noise, grain, static, motionless, still frame, overall grayish, worst quality, low quality, JPEG compression artifacts, subtitles, stylized, artwork, painting, illustration, cluttered background, many people in background, three legs, walking backward, zoom out, zoom in, mouth speaking, moving mouth, talking, speaking, mute speaking, unnatural skin tone, discolored eyelid, red eyelids, red upper eyelids, no red eyeshadow, closed eyes, no wide-open innocent eyes, poorly drawn hands, extra fingers, fused fingers, poorly drawn face, deformed, disfigured, malformed limbs, realistic penis, thighs, fog, mist, eyelashs, realistic eyelashes, detailed eyelashes, voluminous eyelashes, blush,If something like fog or mist appears, please add it to the negative prompts.
⚠️ Disclaimer:
All characters are AI-generated and do not represent real people.
Content generated by this model is AI-created and may not be entirely accurate or reflect reality. Please do not rely on it as factual.
You are solely responsible for any copyright infringement or other intellectual property issues arising from content you generate using this model.
We do not guarantee the continuous availability or error-free operation of this model. We reserve the right to modify or terminate the service at any time.
You are solely responsible for any content you generate and how it is used.
This LORA is for academic exchange only and has not been shared on any other websites. Please do not repost or reupload it. It is only permitted for use on Civitai
Description
The V1.0 No Emotions is my very first and most flawed version, created using only 15 anime images I generated. It might lead to darker or slower frames. If you choose to use this version, please do not include any emotional prompts—just describe the cumshot action. Pairing it with WAN CUMSHOT should help resolve the darkening and slowdown issues.
LoRA Overview｜Anime Cumshot Aesthetics – Precision Load
Anime Cumshot Aesthetics – Precision Load is a LoRA specifically trained to enhance the visual and stylistic quality of cumshots in anime-style videos, focusing on density, precision, impact, and aesthetic realism.
This model was developed to complement existing cumshot LoRAs like WAN CUMSHOT by focusing specifically on anime-style aesthetics and short-form timing. While general-purpose models aim for broad adaptability, Anime Cumshot Aesthetics – Precision Load targets refined features such as thickness, directional accuracy, and artistic expression, delivering paste-like cumshots with strong visual impact in tightly timed scenes.
compatible with real-person styles as well. It performs best when both male and female subjects are present
FAQ
Comments (23)
Thanks, we need more fine-tuned versions of sex positions for anime.
Thank you, and please feel free to share any problems or questions as well.
If you have any good experience or insights, please feel free to share.
Looks great can't wait to try, nice work thanks for the share.
Thank you, and please feel free to share any problems or questions as well.
If you have any good experience or insights, please feel free to share.
Great project! I hope you keep working on this and iron out some of the flaws. One major issue seems to be that cum often just appears on the face, as is evident in some of your own preview pictures. Very good start, nonetheless! I'll try generating something fun with it.
Yes, this is because I lack sufficient material. It's really hard to get good material, so I can only try with the minimum for now.
What I want to know now is how to reliably generalize positions and specifically exclude slow motion and the screen turning black. These are the problems I'm currently learning about. If you have any good experience or insights, please feel free to share.
I'm not sure if having enough positions will truly allow for generalization.
Yeah that issue exists with the other cumshot loras as well. It's really difficult to iron out even with a good amount of data. This version is great, but the main issue in this compared to other cumshot loras, is that the person doesn't really react to the cum hitting them. They are a statue that keeps their same emotion as when it started. That might be helped by more data. Check out the main video for Wan Cumshot to see an example of reacting.
@Jellai > They are a statue that keeps their same emotion
This has its own use cases... 😏
@Jellai Yes, that's because it's my first training, and I wasn't sure what the correct approach was. So, I didn't start with 5-second footage; I only began training with 3-second clips. This only resulted in training the actions. It's also possible I didn't add descriptions of emotional movements to the tagging content. However, the first three seconds of my footage basically felt like there wasn't enough time to react. This is also due to my lack of material. Most importantly, there's very little uncensored anime footage. So, I had to create it myself. There's rarely any pure cumshot anime footage that's also uncensored, which is why I had to make my own and then select what I felt was the best quality material. Therefore, if I want emotional actions paired with cumshots, that would be ideal.
@FLOW0308 It's a very impressive attempt. And yeah, it's really difficult finding the kind of footage you need. I wonder if there's stuff in the Live2D uncensored patched games.
@Jellai If you can find similar materials or website sources, or if you discover places that can provide similar materials, please let me know. I would be very grateful! Thank you
I just heard someone say that using one's own AI-generated works as training material might lead to side effects like slower performance and amplified problems. They said, "Inbreeding AI is stupid and causes all kinds of issues." If that's true, then I'm finished, I'll have no material to use.
@FLOW0308 That's probably more related to training checkpoints on big batches of AI generated images without quality control. Adding desired generated data is perfectly fine and common practice. The general best practices apply: select data carefully, tag appropriately, select best epoch where learning effect of a concept is maximized while overtraining is minimized.
@xnapx A girl is kneeling. The man is stroking his penis. He ejaculates on her face and chest. The cum is thick and clings to her skin like paste, slowly running down.
This is one of my tagging descriptions; the content is all pretty similar. For my subsequent training materials, I'll be adding emotions and actions.
This is 3-second source material. I'm not sure if there's an issue with it. What do you think? Also, is there a general understanding that LoRAs trained entirely on 3-second video material cannot produce 5-second videos? Because when I've tried, 5-second videos sometimes have problems. Have you encountered issues like this if you were to use my LoRA alone?
That's strange. The LoRA I just used was able to create a 5-second video on its own. Could it be because I randomly added some emotional/action reaction keywords to the prompt? Although it still looks like a statue, since I didn't include emotions or actions in the training data.
@FLOW0308 I can't speak to WAN lora training from experience, since I'm still (very slowly) collecting material. WAN itself has surprisingly broad prompt understanding as it is, so even with your lora as the sole finetune, as well as a lucky noise seed, you CAN get reactions in the generation. Also, I assume that WAN Cumshot was trained on material including strong reactions. There's even a small overtraining effect to it, as it's hard to get more still results from that one alone. In the end, all lora training always comes with the risk that a concept is learned to a too low or too high degree That's just the nature of the beast. From my experience with image lora, I can just encourage you to keep trying and be okay with unsuccessful runs sometimes. Nothing you can do, aside from selecting the source material and tagging appropriately. As long as you keep trying, you WILL eventually get something good. In fact, this lora IS good already and allows for generations that are distinct from WAN Cumshot. I'm looking forward to your progress. Don't get discouraged by setbacks or random comments. You're doing well!
@Jellai I've tried updating to a version that seems to respond better to emotions (or handle emotional content better). I'm not sure if it's perfect, but it should have fixed the issue with the screen becoming dark. As for the speed, I still feel it's a little bit slow, and I can't figure out what the problem is.
@FLOW0308 This adds a lot of life to the scene. I'm impressed by what you've put together!
I've been trying to train another LORA for off-screen ejaculation. After testing, I've noticed that the generated videos still feel like the action is slowed down. I'm now unsure if it's due to insufficient training material or something else.
The video footage I created myself, which I'm using as training material, has a very natural and normal sense of speed. However, after training the LORA with this material, the LORA itself can generate what I want (the content is fine), but the problem is that the action in the generated videos feels slowed down.
I genuinely don't know what's causing this issue. I've checked my source material; they are all natively generated videos from ComfyUI, originally at 16 FPS and 3 seconds long, which I've used for training. I'm using Musubi Tuner, but specifically the GUI version by the author 'ttplanet'.
Wan2.1/Hunyuan Video Lora Trainning with GUI in Windows | Civitai
It's really strange. Has anyone else experienced this?
Here is my configuration:
# resolution, caption_extension, batch_size, enable_bucket, bucket_no_upscale must be set in either general or datasets
# general configurations
[general]
resolution = [256, 256]
caption_extension = ".txt"
batch_size = 1
enable_bucket = true
bucket_no_upscale = false
[[datasets]]
video_directory = "F:\\musubi-tuner_GUI-Wan\\train\\anime cumshot"
cache_directory = "F:\\musubi-tuner_GUI-Wan\\train\\anime cumshot\\cache"
target_frames = [1, 49]
frame_extraction = "head"
num_repeats = 5
# other datasets can be added here. each dataset can have different configurations
```"
thx! 720p?
My computer can't render 720P, only 480P.
@FLOW0308 You can use google colab for your final results as it offers way below runpod or Massed Compute <$0.3/hr for good old a100 with 40gb vram, directly work on 720p fp16 (32gb). (pricing is differ locally so best to check)
@spittreyways I've looked into cloud training, but it's tough; my English is so bad that I can barely understand their cloud operation explanations.
Details
Files
Anime CumShot-V7 -000018_converted.safetensors
Mirrors
Anime CumShot-V7 -000018_converted.safetensors
Anime CumShot-V7 -000018_converted.safetensors
Anime CumShot-V7 -000018_converted.safetensors
Anime CumShot-V7 -000018_converted.safetensors
Anime CumShot-V7 -000018_converted.safetensors
Cum - Anime Cumshot Aesthetics – Precision Load Anime CumShot-V7 -000018_converted v1 (no emotions).safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.