SmoothMix Animations LTX
8451°
<smoothmix-ltx23>
Apps that support ModelTrends tags let you run/install models by copying this code in your prompt with no setup. Look for our icon in apps that support it, like Prism (below).
Run this model
Offers / Ads
Easy Creator (Prism) Web
Unlimited · flat fee
Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.
PirateDiffusion Telegram
Unlimited · flat fee
Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.
Pro studio (SpyGlass) Web
Unlimited · flat fee
Best for power users. Full control over models, settings and workflows in a browser studio.
Discord bot (Vector)
Unlimited · flat fee
Best for communities. Add it to your own server and run any workflow from a channel.
Unified Editor Web
Unlimited · flat fee
One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.
Civitai Web
Pay per use
Generate on Civitai's own site; every image is paid for with Buzz credits.
Local apps
Requires setup
Set up local programs if your computer has capable hardware.
ModelDuel Web
Pay per use
Generate the same prompt on up to 50 checkpoint/base models at a time.
By DigitalPastel - SmoothMix Animations LTX
Creator notes
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! =)
Trigger words
smoothmixanime
anime style
smoothmixrealism
realistic style
SHA256
02A9E8D1884DB23E022828F7D7221D5C93FC3C8D7924A022D8E4AB0A81EBB31F
SmoothMix Animations LTX Popularity Trend
Heat score since 22 Apr 2026
Heat score
8,451°
This week
▼
0.1%
8,453° then, 8,451° now
This month
▼
0.3%
8,459° then, 8,451° now
Past year
n/a
Wasn't released/tracked
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.
+1,096°
Civitai downloads
3,967 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.
+371°
Likes
295 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.
+43°
Adoption rate
About 3 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.
+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.
−159°
Age
−159° because the Ltx2 weights came out in 2025. Every model inherits the age of the weights it is built on: 150° a year, up to 750°, and it keeps growing until then. Without it the top of the list would be 2022 and 2023 checkpoints on the strength of downloads that had years to pile up.
Show detailed breakdown
Every number on this site can be checked. This model's heat score is 8,451°, 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.
- 1Start 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
- 2Add the downloads.3,967 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.+1,096°8,096°running total
- 3Add the likes.295 likes and thumbs up, at half the weight of a download.+371°8,467°running total
- 4Add the adoption rate.About 3 downloads a day right now, measured between two readings, at a quarter of the weight.+43°8,510°running total
- 5Family boost.An open, bounded nudge for LoRAs of a family this site is pushing forward right now.+100°8,610°running total
- 6Take off the age.The Ltx2 weights came out in 2025: 150° a year, up to 750°, growing until then.−159°8,451°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.8,451°
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
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.
Settings
Size
768x1024
Prompt
Workflow included
Settings
Sampler
DDIM
Steps
8
Guidance
2
Size
1024x1408
Prompt
((Video and audio styling: An ultra-realistic high-production-value first-person POV video, amature style, realistic ordinary male and female voices:2))
((Scene: The POV viewer sitting in an office chair is stroking his thick cock while he looks up at a japanese female coworker wearing glasses, her hair tied in a bun, and a secretary outfit using his computer's keyboard. He grabs his cock with his hand strokes it up and down letting it get more erect and harder as his coworker watches him in his chair.
Japanese coworker, standing at the desk she speaks shyly and coyly with a thick heavy Japanese accent, soft feminine lilt, gentle embarrassed tone and cute natural pauses, saying “Ai soto yuu wanto herupu wizu yoo konpyuutaa! …in-suteddo yuu ah go-eeng tu get me een-to toraburu!"
((She kneels down in place, keeping her blazer on, light blue blouse is opened to reveal her big natural breast's cleavage, and looks at the penis, she giggles softly while she stares at his big veiny erect penis. Her eyes flicking down then back up, then continues breathily, “…butto… itsu soo biggu….” Perfect lip-sync, authentic Japanese pronunciation on the English words.
He strokes his cock more as she watches.
She watches and says shyly and coyly with a thick heavy Japanese accent, "Sutorooku itto foa mii…" She get's turned on and sensually touches herself as he strokes faster.
She looks, coy and naughtly says "…aa Doo yuu wanto tu kamu on mai feisu? …Zatto wuddo bii soo hotto!" She then opens her mouth wide making an ahegao style face and sticks her tongue out far letting drool drip down her tongue while moaning sexually, and crossing her eyes crosseyed style. "ahh… kao ni bukkaketeo…" Letting the man stroke his penis right in-front of her face.
POV viewer is wildly stroking his penis for her.:2))
japanese woman coworker makes constant loving gaze into viewers eyes,
pov viewer's body stays in consistent position on chair, only to swival left or right, no up or down movement,
penis interacting with skin, realistic collision physics, detailed skin deformation and rippling on impact, moving up and down the entire shaft, glistening penis, accurate realistic clothing realistic accurate angle perspective, correct proportions, realistic muscle movements, realistic body jiggle and bounce, dynamic hair movement, realistic gravity, consistent Asian woman's face and body, consistent penis shape and firmness, dynamic realistic penis movement realistic movement, dynamic posing, cinematic realism, high-fidelity realistic emotions on both characters — shock, anger, pleasure, surprise, ahegao ecstasy high production value, best quality, ultra-detailed, photoreal ambient background movement, dynamic realistic gravity
Negative prompt
low quality, bad quality, low production value, still image, bad quality, subtitles, watermark, ugly, blur, logo, wordmark, static
Settings
Sampler
DDIM
Steps
8
Guidance
2
Size
1024x1408
Prompt
((Video and audio styling: An ultra-realistic high-production-value first-person POV video with all male audio coming thru an iphone phone speaker, phonecall style:2)),
((Scene: The viewer looks straight down from above as a beautiful asian woman dressed with lingerie with a studded metal dog collar choker and a headband with dog bone designs kneels directly in front of him on her knees inside a softly lit bedroom. She's talking on her iPhone Pro with her boyfriend on the other end of the call, shyly smirking with a loving gaze up at the viewer, her right hand playfully squeezing her breast for a moment and says: “Hey Honey! Guess what I'm doing!” Her boyfriend on the other end of the call answers through the iphone's speaker-phone.
Boyfriend on speaker phone: "I'm not sure, what are you up to?
Girlfriend: "Oh.. something very VERY hard."
Boyfriend on speaker phone: "Are you at work right now?"
Girlfriend: "Yeah... I'M WORKING... HARD..."
At 0:11
((She giggles at her joke and winks at the viewer and tosses her phone out of frame to the left side off camera out of POV view.:2)).
At 0:13 seconds:
She leans in places the phone down, and starts sucking on the penis. giving it a deep sensual blowjob, sucking it hard with gagging and slurping noises while moaning getting the penis glistening and covered in slobber.
at 0:15 seconds:
Boyfriend on speaker phone says: "wait... what are those noises?"
She starts gagging and choking on the penis keeping her head all the way down on the base of the shaft, as she looks directly at the viewer with her eyes watering with a love gaze, tears form and fall down her cheeks as she gags on the cock.
Boyfriend's voice still on speaker phone: "...Hello..Are you there?"
At 0:20 seconds:
She releases and stops giving the blowjob, she gasps moaning in euphoria, drool trailing from her mouth to the penis shaft. She leans back and starts stroking the penis hard giving it a wild handjob. she laughs.))
(consistent iphone size and shape, keeping phone ridgid and solid, no morphing:2),
(penis interacting with skin, realistic collision physics, lips stretching and wrapping tightly around the thick shaft, detailed skin deformation and rippling on impact, lips reacting realistically to the penis's size and shape, penis inserting into lips, penis slowly pushing inside of woman, insertion, moving up and down the entire shaft, dripping wetness all over penis, accurate realistic clothing realistic accurate angle perspective, correct proportions, realistic muscle movements, realistic body jiggle and bounce, dynamic hair movement, realistic spit and drool physics with gravity, consistent Asian woman's face and body, consistent penis shape and firmness, dynamic realistic penis movement realistic movement, dynamic posing, static camera, cinematic realism, high-fidelity realistic emotions on both characters — shock, anger, pleasure, surprise, ahegao ecstasy high production value, best quality, ultra-detailed, photoreal ambient background movement, consistent background, dynamic realistic gravity:2)
Negative prompt
low quality, bad quality, low production value, still image, bad quality, subtitles, watermark, ugly, blur, logo, wordmark, static
Run Locally
How to install
How to install a LoRA: folders, file checks and first use in ComfyUI, Forge, Automatic1111 and Draw Things
Sep 24, 2025
SmoothMix_Animations_LTX2.safetensors
Downloads are served by Civitai. Some creators ask for a Civitai login first.
SmoothMix Animations LTX is a LoRA for the Ltx2 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Ltx2 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153