eros 1.0 - i2v without audio.
It already works fine this just makes it compatible and fluid with 10eros
1.0 - i2v with audio.
Attempt to add audio , might be over trained set to 0.8
0.9 - i2v no audio.
i2v trained on mix of ai mostly for bouncy look , ty to Allardice
Set 0.5-0.8 strength with keywords or with descriptive prompt for smoother results.
1.0 will also work but has repetitive AI look to it , could be better with other loras.
Start with Riding backshot animation. / Riding frontshot animation. + text.
Description
FAQ
Comments (49)
Can you share your workflow that you used to make these sample videos?
Why did my prompt only write 'Riding frontshot animation', which didn't achieve the effect of you only writing 'Riding frontshot animation'?
Finally, a Lora for LTX2 that actually works great. I've already gotten great results out of this one. I hope you keep updating it and I also hope you add other positions such as missionary and whatnot.
Thx , 2.0 i2v loras still work
you can combine with https://civitai.com/models/2385036/doggy-missionary-3d
might update it later to 2.3 but not planned atm
@blo01 I just tested it and it works! It's about dang time someone cracked the code for LTX2 and this is really great stuff. I hope you keep updating these, your Loras are genuinely the first to give me what I want out of this model and at very high quality too.
1.0 after buzz paid but cannot be downloaded
"code"too_many_requests"message"Your account has made too many requests; try again later."status429"
wf can be downloaded but not the lora...
oh idk could be browser issue
try ctrl+shift+r for hard page refresh
@blo01 yeah it works now! ty!
REALLY REALLY good! thank you , please do some other poses. cheers
EDIT: Workflow is in the training data download!
That said, I used my own workflow and it's drag on drop, and it works great!
This is i2v not t2v
wf is in wf.zip as well or any other i2v should work
Also 100 points is nothing lol , this is cheapest paywall for shortest time just to have people who know what they are doing try it first.
Don't really care about points , post results and I will drop them back.
@blo01 Yeah................I dicked up a setting in my worklfow. This things works great :D
Thanks for sharing the workflow, that helped a lot.
I added the custom audio from Runexx workflows, they are pretty good too (https://huggingface.co/RuneXX/LTX-2.3-Workflows/tree/main)
Hi, Where did you find his workflow ?
@hboxgames132 He's sharing it as "Training Data", yeah it's not obvious but look on the right it's there lol
You also have the choice when you click on that download icon
@Tetsuoo Thanks !!
Excellent LORA! I used version 1.0 and ran the 0.8 weights locally, and the results were very good. Thank you! Also, I would like to ask you, what training tool do you use to train LORA? Could you please tell me the deployment address? I am preparing to train the learning deployment training tool and start training my first LTX2.3 LORA from scratch! If possible, thank you very much!!
Oh, sorry. It's the translation software that's malfunctioning. What I mean is, how can the trainer be deployed locally or in the cloud? What model of Musubi is it using? Or is it the AI-Toolkit?
@wange999 It should run local or on cloud , it's ltx2.3 model
Ai-toolkit is another trainer that supports ltx but check if everything works with audio there , I haven't tested it
@blo01 I only have 16GB of video memory and 64GB of RAM. I'm not sure if I can run the trainer properly. I'm currently looking for a cloud solution, but there are no training tutorials for ltx2.3 on any of our major video platforms!!
@wange999 ostris, runpod, check youTube.
Dude, thank you, finally some good hentai style ltx stuff, god bless you!
wait, this looks and sounds amazing! does ltx2.3 have potential for hentai??
It has all the capabilities — but it really comes down to how much the community is willing to help each other, or how far they're willing to get involved.
100% I made few good ones
i think we need to wait for good loras, and who knows, maybe ltx2.5?
I'm finding this Lora at very low strength (0.1-0.2) can help bring a little jiggle physics into any video, not just sex ones.
nice find , it's just adding vertical motion ,need to try it
you can also rotate image and rotate video back to get funny results
@blo01 Are you prompting any specific for the penis going all the way in? Im struggling there
@redlittlerabbit Not really , if you use other loras they all average so stuff won't go all the way in.
If it's outside use other lora with riding one.
Also it's seed chance and input image angle bound from what I saw.
May want to correct the base model to 2.3
You're right ,thank you
At the moment of release it did have a tag but didn't have a filter added
So I put it in 2.0
thanks for the no audio variant !
It is pretty bad at keeping the face. looks like another person as it goes on. shame.
yeah this wasn't trained for long runs :D
after how many frames does it break for you ?
@blo01 It breaks pretty much instantly on anime styles for me, especially the lips mutate massively. For example this is what it looks like as soon as her mouth moves: https://i.imgur.com/iUPsMVr.png
Got the same issue on the SmoothMixAnimations LoRA, probably affecting style too much. Lowering LoRA strengths helps slightly but it also affects motion quality. I don't know enough about LoRA training etc. but I'd guess that there's a few blocks affecting style too much.
@LastAssignment are you using model with mixed in loras ? or clean one without adding anything to it except this lora ?
@blo01 Clean BF16 dev model. I only really get it working by lowering this LoRA to atleast 0.5 (used 0.8 in the example), motion suffers slightly and style still bleeds through but it's atleast usable this way, motion is MUCH better than without.
It's definitely not easy to get flat anime styles working with mouth movement with the current NSFW LoRAs.
Works great! Fixes the issue of "Exorcist neck" on some other LoRAs where the girl twists her head around impossibly.
Can you share a workflow for this? I want to get started on ltx but all I have is the all in ones which are brutal
Details
Files
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
Mirrors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
ride.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
1.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
Riding pov v1.0 - LTX2.3 - Riding backshot animation,Riding frontshot animation,moaning and wet slapping sounds,heavy breathing,CLAPPING SOUNDS.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
Riding pov v1.0 - LTX2.3 - Riding backshot animation,Riding frontshot animation,moaning and wet slapping sounds,heavy breathing,CLAPPING SOUNDS.safetensors
ltx-2.3-riding-pov-i2v.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
Riding pov v1.0 - LTX2.3 - Riding backshot animation,Riding frontshot animation,moaning and wet slapping sounds,heavy breathing,CLAPPING SOUNDS.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
nsfw_riding_backshot_frontshot_ltx23_v1.0.safetensors
riding.safetensors