Model
.ai
tracking open ai models

2D Anime Style NSFW LORA H3 v0.5 general NSFW

8517°
2D Anime Style NSFW LORA   H3 v0.5 general NSFW
Created by
tazmannner379
on Civitai
by tazmannner379 - 2D Anime Style NSFW LORA - H3 V0.5 - For specific words, it was consistently trained on these terms: penis, vagina, vaginal, testicles, penetration, insert, breasts, bouncing, jiggle, anus, anal, buttocks, plopping sound (for both sucking and penetrating), cowgirl, reverse cowgirl, doggy style, missionary, deep throat, thrust (for thrusting hips), blow job, suck, cum, cumming, deep breathing, heavy breathing, moan, grunt, insert, pull out, tentacle, ass ripple (for jiggling ass cheeks). It is trained on sound: moan, grunt, use "plopping" sounds fucking / sucking sounds.
Creator notes
WARNING: Consider this a beta, it still needs a lot of work. Please follow me on X/Twitter: I am now posting on there more often, you can get early previews of what I'm working on there. It means a lot to grow outside just here. Thank you. Triggers / Tips For style : 2d anime style (always use this). (you can mix styles from other anime with this though with additional style keywords or style loras). For specific words, it was consistently trained on these terms: penis, vagina, vaginal, testicles, penetration, insert, breasts, bouncing, jiggle, anus, anal, buttocks, plopping sound (for both sucking and penetrating), cowgirl, reverse cowgirl, doggy style, missionary, deep throat, thrust (for thrusting hips), blow job, suck, cum, cumming, deep breathing, heavy breathing, moan, grunt, insert, pull out, tentacle, ass ripple (for jiggling ass cheeks) It is trained on sound: moan, grunt, use "plopping" sounds fucking / sucking sounds. Adding other NSFW or motion loras (which are trained on 3d/IRL) will make the generation look less 2d. Just a warning. Recommended use with if you must use a speed up, 20 steps default is best though. 5 steps 0.8 strength on DMAD and 1 strength on this. Euler Beta57. for DMAD though er_sde simple is ok too. V0.5 This went through an additional 9 training attempts! I wanted to apply the knowledge I've learned since I started this lora with a fresh method of training. I bumped up the # of screen captures from the video dataset to around 480 images and videos are the same 422 clips, though I changed the target FPS to 25 to match the source. And overall its trained on higher resolution. This was trained in three stages: Stage 1: Images only training for detail. Using circle stone adapter 1.8k steps (1376x768; 1024x1024) with circle stone labs image adapter Stage 2: Images + video for motion. Same as before but videos at 832x480 124frames added in. Stage 3: Image + video + sound for audio. Switch to Ostris v3 adapter with Audio Layers setting (Attention; mlp;audio), video 0.20 strength and audio 1.0 strength on weights. Each time load from weights, with Automagicv3. I think though the video has drifted a bit, stage 2 had much better penetration. So probably expect a better fixed version soon if additional training will help. If not I may start over from Stage 1 again and do everything with just the Ostris v3 adapter since it can do Stage2/3 together most likely. Overall its more stable in the sense that it has less distortion on the coloring and lines. And I think concepts like bj and hj are stable, penetration suffers the most. Sound is good. Motion in terms of jiggle/bounce I think look quite nice. This is almost 100% upgrade from last version. V0.4 Brushed up the dataset a bit, added in around 10 new videos and like 150 or so new images. I trained the videos and images together, but I think the best way would've been to do images first then add the videos. I restarted training and ran from 0 zero this time instead of loading weights. I wasn't able to get around to fixing paizuri ("tit fuck") and anuses still don't really show up despite making up a large part of the dataset. I think overall its a bump up in improvement from the last version, whatever that version did this can do better now and genitals look better. I'm gonna train it a bit more and see if more steps will help too, as the 23k steps version wasn't all that bad. 19.5k (most stable) is what's uploaded here, and a few other checkpoints in optional files if you wanna test those out too. Samples provided are not cherry picked. V0.3 edit: added 8100 steps checkpoint, use that one, seems better. There is 9450 steps one which may work for i2v better but its not stable, 8.1k I like the best. Added back in general NSFW data, so vagina, cumming, anal etc. are back in the dataset. I also added in an extra 50 or so images, making the total now: 130 images and 412 videos. It can now do pretty much all the stuff the v0.1 could do but actually stable and working now. I didn't have much time to check the checkpoints but the 5k steps one seems stable enough. Some of the samples seem weird with the vagina if you are prompting insertion. That I think can be fixed with better prompting. Sometimes bj the lips dont attach but rerolling seed or adjusting prompt fixes. I'll see if more training steps will help or not. I'll work on another version to improve the vagina shape and try to get the anus to appear, but I think might take a little longer, I'm getting a little burnt out working on this so fast. And I finally feel the lora is in a good place now. Please post your examples and constructive feedback. Did limited tests with lightx 8 step lora, and it does work with this lora (1str light 0.75-0.8 my lora) but you need to play around with the strength of both loras otherwise it goes off the rails. I recommend to not use them as they effect style quite a bit, let me know good settings and I can test. All samples are generated with 20 steps fully no speed ups. I also recommend the euler beta57 scheduler but simple seems more stable now. V0.2 Note: Do not use euler simple otherwise it will be distorted, try euler beta57 (my favorite so far) or some other scheduler/sampler. Strength 1 recommended, maybe 0.75 if you feel distortion too strong but I keep it at 1. Not tested with lightx. I had to go back to the drawing board and start over. I pruned the dataset down to 105 high quality clips involving only hand jobs or blow jobs and truncated them down to 75max frames. I also removed all furry content to remove any confusion for how dicks should be shaped. Then I added in a dataset of uncensored 2d anime style penis images. I also converted my captions from LTX format to H3 format with the help of gemma4 12b. I trained the videos on 672x384 resolution and the images on 1024x1024 resolution. Batch 3 for images, 1 for videos. I adjusted h3_guidance_distillation_scale down from 4 to 3.5. By reducing
Trigger words
2d anime style
3,315 downloads · 253 likes on Civitai
SHA256
2353DE7443B9693A73D23124923B18EAB3F0850A68FC32FD36876537C641A721
2D Anime Style NSFW LORA H3 v0.5 general NSFW Popularity Trend
Heat score since 6 Oct 2026
Heat score
8,517°
This week
▲
72.8%
8,411° then, 8,517° now
This month
n/a
Wasn't released/tracked
Past year
n/a
Wasn't released/tracked
2D Anime Style NSFW LORA H3 v0.5 general NSFW: Heat score since 6 Oct 20267,000°7,425°7,850°8,274°8,699°6 Oct9 Oct13 Oct16 Oct19 Oct22 Oct8,517°ModelTrends.ai
7,000°
Floor
The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.
+1,056°
Civitai downloads
3,315 downloads of this exact version on Civitai. Downloads are the heaviest ingredient and are counted on a log scale: ten times the downloads adds the same 300°, so a model with a million downloads is not a thousand times hotter than one with a thousand. The six download sources share that one term, split between them in proportion to their counts.
+361°
Likes
253 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.
+100°
Family boost
+100° because this is a LoRA of a family this site is nudging forward right now. It is a bounded nudge inside the score and is listed here openly; it can never hide a model or outweigh a thousandfold difference in downloads.
Show detailed breakdown
Every number on this site can be checked. This model's heat score is 8,517°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.
  1. 1
    Start at the floor.
    Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.
    7,000°
    running total
  2. 2
    Add the downloads.
    3,315 download-equivalents in all, from Civitai downloads. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
    +1,056°
    8,056°
    running total
  3. 3
    Add the likes.
    253 likes and thumbs up, at half the weight of a download.
    +361°
    8,417°
    running total
  4. 4
    Family boost.
    An open, bounded nudge for LoRAs of a family this site is pushing forward right now.
    +100°
    8,517°
    running total
  5. =
    The heat score.
    Where this model stands on every list of this site. Nothing else adjusts it.
    8,517°
Glossary: the terms used here
Heat score
One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor
The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents
Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale
Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes
Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate
How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated
Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder
Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde
A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites
Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens
A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint)
The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding
Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights
The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age
Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost
A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score
A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period)
A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend
How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model
The middle of the catalog: half the models with a figure grew faster over the period, half slower.
How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Size
1920x1080
Prompt
subject_definitions: <Subject 1> is char_emilia from the character sheet in <Picture 1>, a young woman with long silver hair, a thin braid running across the top of her head like a crown, and a long braid down her back, a white flower ornament with trailing purple ribbons on her right side and a small white X-shaped hairclip on her left, pointed elf ears, and purple eyes. She wears a long white hooded cloak fastened at the chest with a round gold brooch, a white off-the-shoulder top with scalloped ruffled edges and a high white collar fastened by a gold clasp, puffy white sleeves with pink-and-white striped cuffs, a purple full-body bodysuit, and white knee-high boots with purple V-shaped trim and purple soles. <Subject 2> is char_subaru from the character sheet in <Picture 2>, a young man with short spiky black hair and brown eyes, wearing a bright orange scarf wrapped around his neck and knotted at the back, a green jacket worn open over a beige button-up vest and a dark undershirt, a brown belt, dark baggy trousers, and brown lace-up boots. <Subject 3> is the forest shrine setting from <Picture 3>: a wide, moss-covered grey stone staircase rising toward an enormous ancient tree with a tangle of thick twisting roots and a dense green canopy, low stone walls on either side, lush green bushes and grass in the foreground, two square stone pillar caps framing the bottom of the stairs, and hundreds of warm glowing golden firefly lights drifting through the air in a dim, teal-green twilight. <Audio 1> is the voice-timbre reference for <Subject 1> (S2). <Audio 2> is the voice-timbre reference for <Subject 2> (S1). summary: [reference generation + audio reference] The target video shows <Subject 2> and <Subject 1> walking into <Subject 3> and stopping in front of the stone staircase, where they break the fourth wall and speak directly to the viewer in Japanese with English subtitles, across four shots, keeping both characters' appearance and outfits from their character sheets and the setting from <Picture 3>, with <Audio 2> guiding the voice of <Subject 2> and <Audio 1> guiding the voice of <Subject 1>. retention_analysis: <Subject 1> (appears in [Shot 1], [Shot 3], [Shot 4]): fully_preserved - the long silver hair with crown braid and back braid, white flower ornament with purple ribbons, X hairclip, elf ears, purple eyes, white hooded cloak with round gold brooch, white off-the-shoulder scalloped top with gold collar clasp, striped cuffs, purple bodysuit, and white boots with purple trim from the character sheet are retained. <Subject 2> (appears in [Shot 1], [Shot 2], [Shot 4]): fully_preserved - the short spiky black hair, brown eyes, orange scarf, green jacket over beige button-up vest, brown belt, dark baggy trousers, and brown lace-up boots from the character sheet are retained. <Subject 3> (appears in [Shot 1], [Shot 2], [Shot 3], [Shot 4]): fully_preserved - the mossy stone staircase, giant ancient tree with twisting roots, low stone walls, foreground bushes, stone pillar caps, and drifting golden firefly lights in teal-green twilight from <Picture 3> are retained. <Audio 1>: reference - its voice timbre guides the dialogue delivery of <Subject 1> without copying the original signal. <Audio 2>: reference - its voice timbre guides the dialogue delivery of <Subject 2> without copying the original signal. detailed_description: The target video is in 2d anime style, rezero style, set at twilight in a forest shrine, lit by a soft teal-green ambient glow and hundreds of warm golden firefly lights drifting through the air. [Shot 1] A static wide shot frames <Subject 3>: the moss-covered stone staircase rising toward the enormous ancient tree with its twisting roots, low stone walls and lush bushes on either side, and two square stone pillar caps in the near foreground, with golden fireflies floating slowly across the frame. <Subject 2>, char_subaru, the young man with short spiky black hair, a bright orange scarf, and a green jacket over a beige vest, strides in from the right side of the frame with a confident bounce, and <Subject 1>, char_emilia, the silver-haired elf girl in the long white hooded cloak with the round gold brooch over her white scalloped top and purple bodysuit, walks in gracefully from the left, her long braid swaying behind her. They meet in the center between the stone pillar caps at the foot of the stairs, turn to face the camera side by side, and the fireflies drift around them as their footsteps settle on the stone. [Shot 2] At 00:02.000, the camera cuts to a medium shot of <Subject 2> facing the viewer directly, golden fireflies glowing soft and out of focus behind him against the giant tree. He flashes a big, cocky grin, throws a thumbs-up at the lens, and leans in slightly as the camera pushes in with small amplitude. <Subject 2> (S1) announces to the viewer with energetic, brash delivery in the young male voice timbre referenced from <Audio 2>, <d>[Japanese] Taz-san no atarashii LoRA wo shoukai suru ze! chotto supaishii na yatsu da!</d> English subtitles appear at the bottom of the frame reading "Introducing a new LoRA by Taz! Something spicy!" [Shot 3] At 00:05.200, the camera cuts to a medium close-up of <Subject 1> facing the viewer, the white flower ornament and purple ribbons in her silver hair lit warmly by a firefly drifting past her cheek. She blinks her purple eyes innocently, tilts her head, and touches one finger to her chin in earnest puzzlement. The camera holds a static shot. <Subject 1> (S2) asks the viewer with soft, gentle, sincere delivery in the young female voice timbre referenced from <Audio 1>, <d>[Japanese] supaishii? toogarashi mitai ni?</d> English subtitles appear at the bottom of the frame reading "Spicy? Like a hot pepper?" [Shot 4] At 00:07.500, the camera cuts to a medium two-shot of <Subject 2> and <Subject 1> standing side by side at the foot of the stone stairs, fireflies drifting around them. <Subject 2> leans toward the camera with a sly, knowing smirk, raising one hand beside his mouth as if sharing a secret with the viewer, while <Subject 1> glances at him with a confused little frown. The camera pushes in with small amplitude at slow speed. <Subject 2> (S1) says to the viewer in a lowered, teasing tone, still in the voice timbre referenced from <Audio 2>, <d>[Japanese] mou H3 de te wo tsunagu dake ja nai, tte koto sa.</d> English subtitles appear at the bottom of the frame reading "Let's just say you do more than just hold hands with H3 now." He straightens up, winks, and points down toward the bottom of the frame as <Subject 2> (S1) adds brightly, <d>[Japanese] kuwashiku wa rinku wo chekku shite kure yo!</d> English subtitles appear at the bottom of the frame reading "Be sure to check the link to find out." <Subject 1> tilts her head at him, still puzzled, through the 12.000-second mark. overall_soundscape: Quiet twilight forest ambience with soft crickets, gentle rustling leaves, and a faint breeze runs throughout. Footsteps on stone and the light swish of a cloak and jacket accompany their entrance, followed by small fabric rustles as they gesture. non_diegetic_music: A light, bouncy pizzicato-string and glockenspiel loop at a moderate tempo, staying low under the dialogue and adding a short plucked flourish on the final wink.
Settings
Sampler
Euler
Steps
20
Seed
894465764556483
Size
1376x768
Prompt
integrated_multimodal_description: [Shot 1] 2d anime style, rezero style, a medium close up short of a young elf woman with light green hair in a french maid uniform as she leans against the side of a stone bridge in a forest while pulling down her blouse to expose her large breasts and nipples with bounce and jiggle from the motion. a man shown only from the waist down. he wears only a jacket and is naked otherwise as he enters the scene with an erect penis. Calmly the woman (S1) says: <d>[English] It's time for master's service.</d> as she strokes the penis and then she gives the penis a blow job. [Shot 2] At 00:04.000, the shot cuts to a first person point of view from the man's perspective shot looking down at the woman woman giving him a hands free deepthroat blow job. As she looks up at him she gives a double peace sign as she her large breasts press against his lower thighs and his penis slides in and out of her mouth. [Shot 3] At 00:07.000, the shot cuts to a dutch angle low shot showing the maid leaning on the side of the stone bridge facing away from the viewer with her dress pulled up exposing her buttocks, vagina, and anus. The man comes in behind her buttocks and inserts his erect penis into her vagina while they have doggy style vaginal sex. He penetrates her vagina and thrusts his hips while keeping one hand on her buttocks. The motion causes the woman to moan and her large breasts to bounce and her buttocks showing a visible ass ripple from the thrusting motion as she moves. [Shot 3] At 00:10.000, the shot cuts to a profile medium shot of the woman still bent over the stone wall as she gets up releasing the man's penis from her vagina as she turns to face the man's penis. She brings one hand up to grab the penis at the base as a single thick white string of cum shoots from the penis into the air and lands onto her lips and chin. She brings one hand up to catch the cum dripping from her chin onto her large breasts as she smiles while looking up at the man with a blushing face. [Shot 4] At 00:13.000, the shot cuts to a whide shot from behind at a dutch angle showing the maid now fully clothed and the man also fully clothed wearing black pants and a black jacket and has long grey hair in a pony tail walking down the bridge off into the forest in the distance. The maid is shorter than the man and holds his arm lovingly as they walk off into the setting sun distance. overall_soundscape: Forest ambient sounds, bird tweeting, female moaning, heavy breathing, plopping sounds from the vaginal penetration, plopping sounds from the blow job. non_diegetic_music: n/a
No prompt was shared with this render.
Settings
Size
672x928
Prompt
dynv2. For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced. summary: [keyframe completion + reference generation] A 6-second high-speed explicit sex scene. The woman remains on top in a full nelson and drives continuous rapid vertical penis motion while being penetrated. Soft muffled moans throughout. Maximum speed from the first frame. detailed_description: The target video is a continuous 6-second explicit sex scene at real-time speed with no slow motion. [Shot 1] The shot opens matching the reference pose: <Subject 1> is straddling <Subject 2> in a full nelson.Anger girl. His cock is already fully inserted deep inside her anus and stays clearly penetrating her for the entire duration. From the very first frame he drives continuous rapid vertical penis lifts and drops with short aggressive strokes, minimal dwell time, and instant rebound. Maximum high-cadence rhythm is maintained without any build-up. Her breasts bounce and shake heavily with every impact. She lets out continuous soft muffled moans and breathy whimpers while keeping her eyes on the camera. The camera holds a low-angle full-body view looking up at her, clearly showing her face, bouncing breasts, and the rapid wet penetration through 00:6.000. overall_soundscape: Dense rhythmic wet skin-on-skin impacts are tightly synchronized with every rapid stroke. Continuous soft muffled female moans and heavy breathing mix with the impacts. No dialogue. non_diegetic_music: None.
Settings
Size
672x928
Prompt
dynv2. For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced. integrated_multimodal_description: [Shot 1]. The scene shows intense intercourse with both characters nude and completely exposed.goblin's large erect penis penetrates deep into her wet anus. He thrusts in and out rhythmically, goblin's shaft sliding in and out of her tight entrance. Her anus grips and squeezes around goblin penis with each powerful thrust, creating intense pleasure. goblin occasionally goes deeper, goblin's full length disappearing inside her. overall_soundscape: Heavy wet rhythmic thrusting sounds, soft flesh impacts, continuous heavy breathing mixed with muffled gasps and moans, and the light sound of dripping fluids.ass jiggle. non_diegetic_music: N/A
Settings
Size
672x928
Prompt
dynv2. For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced. integrated_multimodal_description: [Shot 1] . The scene shows intense intercourse with both characters nude and completely exposed.The girl extremely angry, His large erect penis penetrates deep into her wet pussy. He thrusts in and out rhythmically, his shaft sliding in and out of her tight entrance. Her pussy grips and squeezes around his penis with each powerful thrust, creating intense pleasure. He occasionally goes deeper, his full length disappearing inside her. non_diegetic_music: N/A
Settings
Size
672x928
Prompt
dynv2. For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced. summary: [keyframe completion + reference generation] A 4-second high-speed explicit sex scene. The woman remains on top in a full nelson and drives continuous rapid vertical penis motion while being penetrated. Soft muffled moans throughout. Maximum speed from the first frame. detailed_description: The target video is a continuous 6-second explicit sex scene at real-time speed with no slow motion. [Shot 1] The shot opens matching the reference pose: <Subject 1> is straddling <Subject 2> in a full nelson.Anger girl. His cock is already fully inserted deep inside her anus and stays clearly penetrating her for the entire duration. From the very first frame he drives continuous rapid vertical penis lifts and drops with short aggressive strokes, minimal dwell time, and instant rebound. Maximum high-cadence rhythm is maintained without any build-up. Her breasts bounce and shake heavily with every impact. She lets out continuous soft muffled moans and breathy whimpers while keeping her eyes on the camera. The camera holds a low-angle full-body view looking up at her, clearly showing her face, bouncing breasts, and the rapid wet penetration through 00:4.000. overall_soundscape: Dense rhythmic wet skin-on-skin impacts are tightly synchronized with every rapid stroke. Continuous soft muffled female moans and heavy breathing mix with the impacts. No dialogue. non_diegetic_music: None.
Settings
Size
672x928
Prompt
dynv2. For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced. summary: [keyframe completion + reference generation] A 4-second high-speed explicit sex scene. The woman remains on top in a full nelson and drives continuous rapid vertical penis motion while being penetrated. Soft muffled moans throughout. Maximum speed from the first frame. detailed_description: The target video is a continuous 6-second explicit sex scene at real-time speed with no slow motion. [Shot 1] The shot opens matching the reference pose: <Subject 1> is straddling <Subject 2> in a full nelson.Anger girl. His cock is already fully inserted deep inside her anus and stays clearly penetrating her for the entire duration. From the very first frame he drives continuous rapid vertical penis lifts and drops with short aggressive strokes, minimal dwell time, and instant rebound. Maximum high-cadence rhythm is maintained without any build-up. Her breasts bounce and shake heavily with every impact. She lets out continuous soft muffled moans and breathy whimpers while keeping her eyes on the camera. The camera holds a low-angle full-body view looking up at her, clearly showing her face, bouncing breasts, and the rapid wet penetration through 00:4.000. overall_soundscape: Dense rhythmic wet skin-on-skin impacts are tightly synchronized with every rapid stroke. Continuous soft muffled female moans and heavy breathing mix with the impacts. No dialogue. non_diegetic_music: None.
Run Locally
NSFW_ANIME_H3_V16-step00002250.safetensors
285 MB · SafeTensor · fp32
Downloads are served by Civitai. Some creators ask for a Civitai login first.