Model
Trends
.ai
Model
Trends
.ai
die besten Open-Source-KI-Modelle
Autoplay
Lokal ausführen
SmoothMix_Animations_LTX2.safetensors
1.26 GB · SafeTensor · bf16
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.
AD
Auf Graydient installieren / ausführen
Mitgliedschaft erforderlich
<smoothmix-ltx23>
Über dieses Modell
LTX2 · LoRAs
Erstellt von
DigitalPastel
auf Civitai
By DigitalPastel - SmoothMix Animations LTX
Notizen des Erstellers
SmoothMix Animations LTX "Epic stuff or lewd stuff... make your choice!" Its still not on the same level as the WAN 2.2 version. LTX is very stubborn. T_T So its still a WIP! The main problem is the inconsistency of the results and LTX has many little configurations, both in prompting and setup, that can really affect the results. Testing it properly is kinda of a pain. =/ But its still possible to make alot of fun stuff. There is a lot to explain so lets get started! - ComfyUI Workflow Settings All videos on all Showcases used this setup: ->Workflow: on its default settings (Check the workflow Showcase for more examples); ->Model: ; ->Lora: set to 0.5 With SmoothMix LTX set with 0.8 or 1.0 weight. - Trigger Words The Loras use the following trigger words: 'SmoothMixAnime' and 'Anime Style' - Will make the video have the style of SmoothMix Illustrious/NoobAI/Illustrious2+NoobAI, I recommend using both; 'SmoothMixRealism' and 'Realistic Style' - Will make the video have the style of SmoothMix Realism, I recommend using both. - Img2Vid and Txt2Vid Its primary usage is for T2V. LTX 2.3 seems to have a tendency towards realism, causing some facial distortions on semi-realism/anime images on animations. Try using this Lora with the 'SmoothMixAnime' with weight of at least 0.5 - it might help aliviate that. For T2V I recommend using at least 0.8 weight for most cases. - Limitations So far, LTX is proving to be very annoying for trainning SmoothMix Animation. Using the same dataset with same prompts did not work at all - so making a completely new dataset of videos was necessary. After a few tests this Lora was the best result so far - but its still not as 'energetic' as the Lora for WAN 2.2. The main issue so far is the inconsistency: - Bouncing and movement: The bouncing is nowhere near as it should be (NOOOOOO!!!! T_T). You can still prompt it and get a great results but it doesn't happen everytime. Movement can still be very stiff. - Uncensoring: The uncensoring - overall - works but sometimes can make some weird stuff. (NOOOOOO!!! T_T). So its still not where I want it but it should work well most of the times. I added the male dataset used on Futanaris and Males Lora for WAN 2.2 to uncensor the guys as well but it can only create... huh... eldritch tentacle abominations on the guys (NOOOO!!! T_T), so don't even try those... unless you want to make your eyes bleed! I'm trying to avoid needing to train another Lora just for males and futanaris again but it seems it's going to be inevitable. sigh As always feedback is appreciated! I'll be working on this specify project for now. My main goal is improving the dataset for now. So if you have any difficulties on making certain poses/actions be sure to tell me as I'll be taking notes! ^^ Actually I'm still not sure if I just need more videos on the dataset or if the training needs more steps... or both. This Lora is already using more videos than the WAN 2.2 Lora - with higher quality - and yet the results can be very different between the two. The training takes WAY LONGER as well - 30 hours to make this! WTF!? I'm sorry WAN 2.2! Perhaps I treated you harshly! T_T Anyway, this is only possible with your support! =) If you wish to support a bit just visit my page. Any support counts. ^^ Thank you for all your support! Thats all for now! Have fun! =)
Triggerwörter
smoothmixanime
anime style
smoothmixrealism
realistic style
3,912 Downloads · 293 Likes auf Civitai
SHA256
02A9E8D1884DB23E022828F7D7221D5C93FC3C8D7924A022D8E4AB0A81EBB31F
ModelTrends.ai-Modell-ID
#26882
Inhalt melden
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.
Einstellungen
Größe
704x1280
Prompt
smoothmixanime. Anime style. In a sun-drenched, modern kitchen with marble countertops, a young woman with a messy chestnut ponytail is leaning over a bowl of vibrant green kale. She is wearing a soft, oversized cream-colored knit sweater that bunches at her wrists as she vigorously massages the leaves; the rhythmic, wet crunching of the kale and the soft rustle of her sleeves are clearly audible. To her left, a half-cut lemon sits on a wooden board, its zest catching the harsh afternoon sunlight. The muffled chirping of birds from an open window fill the air. As she works, she lets out a quiet, focused breath and a faint, contented hum. She then reaches for a small glass bottle of olive oil, the glass clinking softly against the marble. She tilts the bottle, and a thick stream of golden oil glitters as it pours over the greens with a light, viscous splat. A few droplets of oil catch on her knuckles, shimmering in the warm light while she continues the steady, rhythmic movement of her hands.
Einstellungen
Größe
704x1280
Prompt
smoothmixanime. Anime style. On a high-altitude train hurtling through a sea of neon-blue clouds, a young man with spiky obsidian hair and a high-collared tech-wear jacket is sitting by a massive, curved window. He is gripping a glowing holographic tablet with both hands, his thumbs sliding across the interface with soft, digital blips and high-pitched mechanical whirs. The interior of the cabin is bathed in a dim neon flicker from the passing clouds, casting sharp cyan highlights on his intense, wide eyes and the metallic zippers of his jacket. Outside, the constant, powerful roar of the jet engines and the sharp whistle of wind against the glass create a dense soundscape. He suddenly leans forward, his micro-expressions shifting from concentration to a sharp, toothy grin as he whispers, "Finally... its time..." His voice is a determined, mid-pitch rasp with a slight urban accent. As he speaks, the entire room is illuminated red and an alarm sound can be heard while the train enters a sudden, violent vibration and the entire screen shakes.
Einstellungen
Größe
704x1280
Prompt
Smoothmixanime. Anime style. Inside a dimly lit, high-end recording studio, a musician with silver-rimmed glasses and a charcoal-grey t-shirt is sitting on a tall stool. He is cradling a polished mahogany acoustic guitar, his left hand pressing firmly against the fretboard while his right hand slowly strums a single, resonant chord. The deep, warm ring of the strings vibrates through the silent room, followed by the faint, metallic scrape of his fingers sliding up the neck. He is closing his eyes, his brow furrowed in deep concentration. He leans into the microphone, his lips inches from the mesh pop filter, and begins to sing in a smooth, soulful baritone: "The city light's a lonely sight tonight." As he finishes the line, he lets out a soft, shaky exhale that is captured by the high-sensitivity mic, then he reaches up to adjust the tuning peg, the mechanical gear clicking precisely into place.
Einstellungen
Sampler
Euler
Schritte
31
Guidance
3
Seed
498593598
Größe
768x1152
Verwendetes Gewicht
1
Prompt
A woman with wavy blonde hair and freckles, wearing a flowing off-shoulder white dress, stands by a large wooden window. She looks directly at the viewer, her expression shifting from a soft smile to a hint of disgust as she speaks. The camera holds a static frame, keeping her centered. Warm morning light streams through the glass, illuminating her face and the white flowers in the vase nearby. She speaks with a mature voice, "I know that it must've been devastating to see all those boys taking turns on me last night.” She sighs and continues, “I just want a child I can be proud of. And I can't get that from your seed." The audio includes a soft ambient hum from a nearby window fan, the gentle rustle of leaves outside, and her clear, slightly breathy voice close to the viewer. anime style
Negativer Prompt
worst quality, blurry, jittery, distorted, watermark, inconsistent motion, bad anatomy
Einstellungen
Sampler
Euler
Schritte
30
Guidance
4.5
Seed
446312247
Größe
1152x1728
Verwendetes Gewicht
0.9
Prompt
smoothmixrealism, A curvy woman with wide hips, dark brown skin and long thick box braids walks forward along an autumn city sidewalk. her hips swaying naturally as she strides confidently forward in a steady human pace. She wears a white turtleneck crop sweater with a deep chest cutout, a blue denim vest, a tight blue denim skirt with a waist chain, and thigh-high lace-up denim boots. Her long braids swing rhythmically over her shoulders as she moves, and her thighs jiggle slightly with the motion of her stride. The camera tracks backward in front of her,maintaining a medium-full shot that captures her movement and the texture of her clothing. The background features blurred apartment buildings and fallen leaves scattered on the pavement, creating a dynamic urban atmosphere. She looks directly at the viewer with a confident, seductive smile. Ambient noise of a busy neighborhood fills the air, rhythmic clicking of her high heels on the pavement.
Negativer Prompt
worst quality, low quality, sketch, score_1, score_2, score_3, censored, bald, long waist, long torso, 3d, anime, cartoon, cgi, 2d, tongue in mouth, teeth visible parted lips, bad eyes, unaligned eyes, crooked eyes, bad pupils, face tattoo, forehead tattoo, arm away from body, leather boots, floral lace, frill trimming, narrow hips,
KI-Modelle für Bild-, Video- und Texterzeugung
smoothmix ltx23 ist ein LoRA für die Familie Ltx2 und wird auf ModelTrends.ai gelistet, einem reinen Lesekatalog für Open-Source-KI-Modelle für Bild, Video und Text. Vergleiche es mit anderen Ltx2-Modellen, prüfe den Hitzewert, um den Trend zu sehen, und öffne es auf PirateDiffusion oder BitVector, um es auszuprobieren.
Nach Modellfamilie stöbern
Alle Modelle ansehen