Model
.ai
offene KI-Modelle im Blick

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

8517°
NSFW-Modell. Seine Bilder sind ausgeblendet, solange NSFW aus ist; schalte NSFW ein, um sie zu sehen.
Erstellt von
tazmannner379
auf 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.
Notizen des Erstellers
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
Triggerwörter
2d anime style
3,315 Downloads · 253 Likes auf Civitai
SHA256
2353DE7443B9693A73D23124923B18EAB3F0850A68FC32FD36876537C641A721
Beliebtheitstrend von 2D Anime Style NSFW LORA H3 v0.5 general NSFW
Heat-Score seit 6 Oct 2026
Heat-Score
8,517°
Diese Woche
▲
72.8%
8,411° damals, 8,517° jetzt
Diesen Monat
n/a
Noch nicht veröffentlicht/erfasst
Vergangenes Jahr
n/a
Noch nicht veröffentlicht/erfasst
2D Anime Style NSFW LORA H3 v0.5 general NSFW: Heat-Score seit 6 Oct 20267,000°7,425°7,850°8,274°8,699°6 Oct9 Oct13 Oct16 Oct19 Oct22 Oct8,517°ModelTrends.ai
7,000°
Grundwert
Die Skala reicht von 0° bis 9.999°. Alles unterhalb von 7,000° ist für Modelle reserviert, über die noch keine Quelle berichtet hat. Diese tragen dort eine Platzhalterzahl, damit die Listen vollständig bleiben. 7,000° ist der Punkt, an dem gemessene Daten beginnen: Ein Modell mit echten Daten, aber fast keinen Downloads, sitzt auf dem Grundwert, und die Messungen füllen die Grade darüber. Der Grundwert sagt nichts über das Modell aus; nur die Grade darüber tun das und trennen ein Modell vom anderen.
+1,056°
Civitai-Downloads
3,315 Downloads dieser genauen Version auf Civitai. Downloads sind die wichtigste Zutat und werden auf einer Log-Skala gezählt: Zehnmal so viele Downloads erhöhen den Wert um 300°, sodass ein Modell mit einer Million Downloads nicht tausendmal heißer ist als eines mit tausend. Die sechs Download-Quellen teilen sich diesen Wert anteilig entsprechend ihrer Anzahl.
+361°
Likes
253 Likes und Daumen hoch über die Quellen hinweg. Ein Like zählt halb so viel wie ein Download, auf derselben logarithmischen Skala.
+100°
Familien-Bonus
+100°, weil dies eine LoRA einer Familie ist, die diese Seite gerade besonders fördert. Das ist eine begrenzte Unterstützung innerhalb des Scores und wird hier offen gezeigt; sie kann ein Modell nie verbergen oder einen tausendfachen Unterschied bei den Downloads ausgleichen.
Detaillierte Aufschlüsselung anzeigen
Jede Zahl auf dieser Seite kann überprüft werden. Der Heat-Score dieses Modells beträgt 8,517°, und hier wird er Schritt für Schritt aufgebaut, mit dem laufenden Gesamtwert nach jedem Schritt: der Grundwert, die Grad, die jede Quelle hinzufügt, der Bonus für die Art des Modells und was das Alter seiner Gewichte abzieht. Die Farben entsprechen den Bereichen der obigen Grafik. Das Glossar am Ende erklärt jeden Begriff.
  1. 1
    Starte beim Grundwert.
    Warum 7,000° und nicht null: Die Skala reicht von 0° bis 9.999°, und der Bereich unter 7,000° ist für Modelle reserviert, über die noch keine Quelle berichtet hat. Diese tragen dort eine Platzhalterzahl, damit die Listen vollständig bleiben und niemals über einem Modell mit Daten stehen. 7,000° ist der Punkt, an dem gemessene Daten beginnen. Ein Modell mit echten Daten, aber fast keinen Downloads, sitzt hier; alles, was folgt, ist Messung, und der Bereich über dem Grundwert enthält zehn zehnfache Schritte bei Downloads zu je 300°. Der Grundwert ist für jedes Modell gleich, er entscheidet also nichts; die Grade darüber tun das.
    7,000°
    laufende Summe
  2. 2
    Füge die Downloads hinzu.
    3,315 Download-Äquivalente insgesamt, von Civitai-Downloads. Zehnmal die Downloads ergeben denselben 300°, also zählt die Größe, aber sie dominiert die Bewertung nie.
    +1,056°
    8,056°
    laufende Summe
  3. 3
    Füge die Likes hinzu.
    253 Likes und Daumen hoch, mit der halben Gewichtung eines Downloads.
    +361°
    8,417°
    laufende Summe
  4. 4
    Familien-Bonus.
    Ein offener, begrenzter Schub für LoRAs einer Familie, die diese Seite gerade fördert.
    +100°
    8,517°
    laufende Summe
  5. =
    Der Heat-Score.
    Wo dieses Modell auf jeder Liste dieser Seite steht. Nichts anderes beeinflusst ihn.
    8,517°
Glossar: die hier verwendeten Begriffe
Heat-Score
Eine Zahl dafür, wie viel ein Modell gerade genutzt und gewollt wird, von 0° bis 9.999°. Jede Liste auf dieser Seite, die „heißeste“ sagt, ist danach sortiert und nach nichts anderem.
Grundwert
Die 7.000°, mit denen jedes Modell mit echten Daten startet. Die Skala reicht von 0° bis 9.999°; der Bereich unter dem Grundwert ist für Platzhalter reserviert (Modelle ohne Daten), damit ein Modell mit Daten immer über einem ohne steht. Der Grundwert ist für alle gleich und entscheidet nichts; die Grade darüber sind die Messung.
Download-Äquivalente
Alles, was der Score als Download zählt, zusammengefasst: Downloads selbst, jeder Torrent-Seeder als 1.000, jedes AI Horde-Bild und jeder Lauf auf einer Generierungsseite als eins.
Logarithmische Skala
Gezählt in Zehnerschritten, nicht einzeln: Der Sprung von 1.000 auf 10.000 Downloads bringt genauso viele Grade wie von 10.000 auf 100.000. So verdrängen Riesen nicht alles andere.
Likes
Daumen hoch und Likes von allen Quellen, jeweils halb so viel wert wie ein Download auf der Log-Skala.
Verbreitungsrate
Wie viele Downloads ein Modell gerade pro Tag bekommt, aus dem Unterschied zwischen zwei Messungen einer Quelle. Ein Viertel der Gewichtung des Download-Begriffs.
Gemessen und geschätzt
Gemessen bedeutet, dass es zwei Messwerte einer Quelle gibt und der Unterschied echt ist. Geschätzt heißt, es ist nur die heutige Gesamtsumme bekannt und die Vergangenheit wird über die Lebensdauer des Modells verteilt; die Seite sagt, welche Variante angezeigt wird.
Seeder
Jemand, der eine Kopie der Gewichte online hält, damit andere sie über einen Torrent herunterladen können, oder ein gehosteter Spiegel, der dasselbe macht. Jeder davon zählt als 1.000 Downloads.
AI Horde
Ein Freiwilligennetzwerk, das kostenlos Bilder auf gespendeten Computern generiert. Die Anzahl der Bilder, die es mit einem Modell erstellt hat, ist öffentlich und jedes zählt als ein Download.
Generierungsseiten
Seiten, die eigene Kopien eines Modells hosten und Leute damit generieren lassen, wie PixAI, SeaArt und Yodayo. Ihre Downloads zählen wie bei Civitai und jeder Generierungslauf als ein Download.
OpenRouter Tokens
Ein Textmodell, das über eine API bereitgestellt wird, wie Claude oder GPT, hat keine Gewichte zum Herunterladen, daher wird seine Nutzung in Tokens gemessen: die Textstücke, die es über OpenRouter gelesen und geschrieben hat, einem Gateway, das viele Apps nutzen, in den letzten 30 Tagen. Je 10,000,000 Tokens zählen als ein Download. Quelle: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Vollständiges Modell (Checkpoint)
Die Gewichte selbst, die Datei, die eigenständig generiert. Sie bekommt einen Bonus, weil Add-ons davon abhängen.
LoRA und Embedding
Kleine Zusatzdateien, die die Gewichte von jemand anderem in Richtung eines Stils, Charakters oder Konzepts lenken. Sie können nicht alleine laufen.
Familie und Gewichte
Die Basis, auf der ein Modell aufgebaut ist, wie SD 1.5, SDXL, Flux oder Wan. Jedes Modell erbt das Veröffentlichungsdatum der Gewichte seiner Familie.
Alter
Abzüge je nachdem, wie lange die Gewichte der Familie schon draußen sind: 150° pro Jahr, bis zu 750°. Alte Downloads, die Jahre zum Ansammeln hatten, bleiben oben in der Liste eingefroren.
Familien-Boost
Ein kleiner, begrenzter Schub für LoRAs einer Familie, die diese Seite gerade vorantreibt, immer in der Aufschlüsselung aufgeführt.
Stand-in-Wert
Eine stabile Zahl unter der Mindestgrenze, die einem Modell gegeben wird, über das noch keine Quelle berichtet hat, damit die Listen vollständig bleiben. Sie rangiert nie über einem Modell mit Daten.
Neu! (Schonfrist)
Ein Modell, das weniger als 7 Tage alt ist, zeigt Neu! statt einer Punktzahl und nimmt keinen Platz in den Rankings ein. Seine Punktzahl wird ab dem ersten Tag berechnet, aber ein Modell, das einen Tag alt ist, wächst schneller als alles andere, daher wäre ohne die Wartezeit das #1 Modell der Woche immer das, das gestern herauskam, statt das, das sich eine Woche gehalten hat.
Trend
Wie das Wachstum eines Modells über einen Zeitraum im Vergleich zum typischen Wachstum eines Modells im gleichen Zeitraum ist. Schneller als üblich bedeutet Anstieg, langsamer bedeutet Rückgang.
Typisches Modell
Die Mitte des Katalogs: Die Hälfte der Modelle mit einer Zahl wuchs schneller im Zeitraum, die andere Hälfte langsamer.
Wie sich die Beliebtheit dieses Modells im Vergleich zum Rest des Katalogs entwickelt hat: sein Wachstum bei Downloads, Likes und Nutzung in jedem Zeitraum, gemessen am typischen Wachstum eines Modells im gleichen Zeitraum, mit dem Heat-Score zu diesem Zeitpunkt. Über dem typischen Wachstum bedeutet ein Anstieg, darunter ein Rückgang. Die Vergangenheit wird aus den heutigen Gesamtzahlen, dem ersten Tag des Modells und seiner gemessenen Download-Geschwindigkeit rekonstruiert, wenn zwei Messungen vorliegen; ein Modell, das zu Beginn eines Zeitraums nicht existierte, zeigt n/a an.
Beispielbilder
Prompts und Einstellungen, geteilt von den Leuten, die diese Bilder auf Civitai erstellt haben. Wähle ein Bild, um zu sehen, wie es entstanden ist.
Beispielrender 1
NSFW-Bild, unscharf. Schalte NSFW ein, um es zu sehen.
Beispielrender 2
NSFW-Bild, unscharf. Schalte NSFW ein, um es zu sehen.
Beispielrender 3
NSFW-Bild, unscharf. Schalte NSFW ein, um es zu sehen.
Beispielrender 4
NSFW-Bild, unscharf. Schalte NSFW ein, um es zu sehen.
Beispielrender 5
NSFW-Bild, unscharf. Schalte NSFW ein, um es zu sehen.
Beispielrender 6
NSFW-Bild, unscharf. Schalte NSFW ein, um es zu sehen.
Beispielrender 7
NSFW-Bild, unscharf. Schalte NSFW ein, um es zu sehen.
Beispielrender 8
NSFW-Bild, unscharf. Schalte NSFW ein, um es zu sehen.
Einstellungen
Größe
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.
Einstellungen
Sampler
Euler
Schritte
20
Seed
894465764556483
Größe
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
Zu diesem Bild wurde kein Prompt geteilt.
Einstellungen
Größe
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.
Einstellungen
Größe
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
Einstellungen
Größe
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
Einstellungen
Größe
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.
Einstellungen
Größe
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.
Lokal ausführen
NSFW_ANIME_H3_V16-step00002250.safetensors
285 MB · SafeTensor · fp32
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.