LTX-2 19B — COMPLETE COMMUNITY TOOLKIT
Everything you need to start creating with LTX-2 19B in ComfyUI, gathered in one community-maintained Civitai hub: base models, GGUF and FP8 variants, text encoders, VAEs, LoRAs, upscalers, ControlNet resources and ready-to-use workflows.
IMPORTANT
LTX-2 was created by Lightricks. I am not the original creator of the base model. This page mirrors and organizes useful public files from the official Lightricks ecosystem while also hosting my own workflows and community resources.
Official source: https://huggingface.co/Lightricks
START HERE — CHOOSE ONE MAIN MODEL
You do not need to download every file on this page.
• GGUF Q4_M — Smallest GGUF option for constrained hardware
• GGUF Q6_K — Good balance between size and fidelity
• GGUF Q8_0 — Highest-precision GGUF option, with the largest footprint
• FP8 Distilled — Faster generation and rapid iteration
• FP8 Dev — Full model behavior and maximum workflow flexibility
The distilled workflow is the easiest starting point when speed matters. Choose the full FP8 or higher-precision GGUF variants when final quality and flexibility matter more.
INCLUDED RESOURCES
• LTX-2 19B GGUF models: Q4_M, Q6_K and Q8_0
• Standard and distilled FP8 models
• Gemma text encoders
• Video and audio VAE components
• Distilled, detail-enhancement and camera-control LoRAs
• Spatial and temporal upscalers
• Canny ControlNet
• EKKIVOK text-to-video and image-to-video workflows
COMFYUI QUICK SETUP
1. Update ComfyUI before loading an LTX-2 workflow.
2. For native workflows, open Template Library → Video → LTX-2.
3. For GGUF models, install ComfyUI-GGUF and use Unet Loader (GGUF). Place .gguf files in ComfyUI/models/unet/; recent versions can also expose ComfyUI/models/diffusion_models/.
4. Place LoRAs in ComfyUI/models/loras/ and text encoders in ComfyUI/models/text_encoders/.
5. Load the included workflow, install missing custom nodes through ComfyUI Manager, then restart ComfyUI.
6. Select the downloaded filenames in the corresponding loader nodes. A downloaded filename may differ from the name saved inside an older workflow, so relink it once if ComfyUI shows a missing model.
TROUBLESHOOTING
• GGUF model missing: verify that you are using Unet Loader (GGUF), refresh the model list and restart ComfyUI.
• Red or missing nodes: use Install Missing Custom Nodes in ComfyUI Manager, then restart.
• Workflow asks for a differently named file: select the equivalent file manually in the loader node; you do not need to download the entire repository.
• Out of memory: begin with a smaller GGUF quantization or the distilled workflow, reduce resolution and frame count, and avoid loading unused models simultaneously.
• Need help: include your GPU, VRAM, ComfyUI version, workflow name and exact error message in your comment.
CREDITS AND DOCUMENTATION
• Original LTX project: https://huggingface.co/Lightricks
• Official LTX documentation: https://docs.ltx.video/open-source-model/integration-tools/comfy-ui
• Official ComfyUI LTX-2 guide: https://docs.comfy.org/tutorials/video/ltx/ltx-2
• ComfyUI-GGUF: https://github.com/city96/ComfyUI-GGUF
If this hub or one of my workflows helps you, sharing a result and leaving a review is the best way to support continued updates.
Description
LTX2 - Camera Control - JIB UP LORA
FAQ
Comments (31)
what is this? is this the official LTX 2 or have you retrained it? If you've retrained it, your description just reads like the official LTX 2.
@qek ok? then what is it lol. this looks like someone just copied the default model. there's literally nothing in the description that sets it apart. why would anyone know / want to download this? seems like OP is just collecting buzz for LTX2 model. They should say wtf this is.
@IrakTheOracle it's basically just a 'reupload' so ppl can link the model used when uploading while he can snag some likes and/or buzz.
@janssenbutton like everyone else but not everyone mention original HF repo, i did ;)
Stop Spamming. You do nothing on that platform just uploading images you didn't release any works too. I did. so stop raging thanks. i hate ppl like that they do nothing but complain even if they are in the wrong.
@EKKIVOK I'm not complaining at all. I was literally just answering his question since you didn't fast enough. and who cares what kind of uploads I have? only you care about my profile. for unknown reason.
@janssenbutton Reason is simple: people like always complaining and are negative, even if they release nothing and use other people’s work to do their images. I have nothing against you, but stop the critics about other ppl when you do nothing, just using their works. Just sayin...
@EKKIVOK I'm not using any of your 'work'. I downloaded the model files from official source the day they got released. Just sayin...
@janssenbutton Don't care about that you still use other workf of other creators like me.
so, stop critics and keep using their works on civitai but stop complaining or be like that.
@IrakTheOracle you didn't read the description right ?
@EKKIVOK Thanks for your work, it's convenient for me to drop by here instead of checking every repo whenever a new model's out. Keep going, ignore the haters.
@IrakTheOracle i didn't collected any buzz and i didn't ask for it.
And the main repo links are mentioned in my description (You know the one you didn't read...)
@alistyph883Thanks bro <3 But as i says it's not my work , i just uploaded the most important models to use on civitai. as the regular law of open source granted to do right ? and like everyone else did already before me. and i linked the original HF repo in case if i forgot something to add here.
@alistyph883 how is this hate? I literally just said that I can run the full model unlike him, even tho he has a better videocard. (other comments). and yes, thanks for anyone uploading models to this site. but as you can see here in his recent replies, he claims those uploaded models as HIS WORK.
@janssenbutton U need friends bro. i never say that was my models....
You're just lying here. omg.... you 're just claiming false things to be the good guy xD
But in the fact you're just a random guy who rage for any reasons and say some lies and no sens xD
i never claimed that was my works (link in the description of the original HF repo and even on my workflows) lol. But you didn't knew that ? you don't know how to read ? So it's your problem ;D
You are that type of guy who like create problem even based on false accusation to shine.
But here bro you're false in every way lol. So you're hating for....nothing xD
@EKKIVOK You are that type of guy who likes to edit his replies afterwards. get a hobby. I already said "have a good one" in the other posts. it's pointless talking to you since I dislike repeating. bye
@janssenbutton Bye bye.
As others have mentioned - why not tell people what exactly it is? If it isn't official what does it do different? Please and ty.
About this Version -> Original version. It's written.
@EKKIVOK Ok? Why are you reposting when LTX is already posting themselves?
@mobdik17378 there is no official LTX on civitai. Only HuggingFace. but not a lot of peaople go there and search by them self.
@EKKIVOK https://civitai.com/user/ltxvideo/models?sort=Newest
My mind is getting blown by this model. It really is packed with some creative character reactions and voicings with the right prompts and good video lengths. Kudos to the LTX2 team.
yeah but those models are seriously limitied.... and sometimes just not working especially for Img2Img
@EKKIVOK LTX-2 is more for txt2vid and img2vid.
The developer is really supporting the community on X and other social media platforms. Like any AI models out there, it has its quirks but it has quite a bit of community backing.
@richcz3 yeah sure but you know it's kind of annoying to get some problems like the png "slide view" mode when you expect videos xD
@EKKIVOK I have not experienced that. So I can't comment on that issue. I've made about 400+ iterations using img2vid of various lengths with no issues aside from prompt adherence issues, but that is to be expected.
I use 4090's and a 5090 to render out using ComfyUI. If you are using ComfyUI you may want to consider using the memory edits in the bat file.
@richcz3 can you tell me more about that ? Maybe it's my prompts that not working in Comfyui...
@EKKIVOK There is the --novram and the --reserve-vram 2 options
If you have an nVidia card with16GB or less these two options allow you to use System Ram
You edit your run_nvidia_gpu.bat in Notepad and add either of those two options.
These options allow you to run ComfyUI using System Ram if you do not have enough VRAM on your GPU.
The more System Ram you have the better. 32GB and up of System Ram will help a lot.
Search "ComfyUI --reserve-vram 2 and --novram" on Google for more information
@richcz3 thanks for the info, i have a rtx 5090 ASTRAL and 128Go 6400mhz.
Do i need to put something then ?
Details
Files
ltx219BCompleteToolkitGGUF_ltx2JIBUPLORA.safetensors
Mirrors
ltx-2-19b-lora-camera-control-jib-up.safetensors
ltx-2-19b-lora-camera-control-jib-up.safetensors
109_ltx-2-19b-lora-camera-control-jib-up_jan23.safetensors
ltx-2-19b-lora-camera-control-jib-up.safetensors
ltx-2-19b-lora-camera-control-jib-up.safetensors
ltx-2-19b-lora-camera-control-jib-up.safetensors
ltx-2-19b-lora-camera-control-jib-up.safetensors
ltx-2-19b-lora-camera-control-jib-up.safetensors
ltx-2-19b-lora-camera-control-jib-up.safetensors
ltx-2-19b-lora-camera-control-jib-up.safetensors
VG2-19b-lora-camera-control-jib-up.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.