Source: https://huggingface.co/unsloth/LTX-2.3-GGUF/tree/main
Workflow: https://huggingface.co/RuneXX/LTX-2.3-Workflows/blob/main/LTX-2.3_-_I2V_T2V_Basic_GGUF.json
Distilled version: https://civarchive.com/models/2484503/ltx-23-distilled-gguf-unsloth
💪Train your own model: https://runpod.io?ref=gased9mt
🍺 Join my discord: https://discord.com/invite/pAz4Bt3rqb
Description
FAQ
Comments (23)
👍🏻👍🏻👍🏻
Dead huggingface link
Thanks for that. Do you have a workflow by chance boss?
@BigSad11 Currently using the Basic one with FP8 https://huggingface.co/RuneXX/LTX-2.3-Workflows/tree/main
@FantasticFever Thanks for that man. I appericate it.
Unsloth does not show a LTX-2.3 and the QuantStack are larger than the ones provided here so this seems peculiar.
I tried to make a workflow with no luck.. Does anyone have a workflow?
I used the basic gguf workflow from here without issue, https://huggingface.co/RuneXX/LTX-2.3-Workflows/tree/main
Though it says it can do T2V too, I haven't figured out how, since the built in T2V option doesn't seem to work. So it may only be good for I2V.
When I use @Zabadu workflow and replace the ltx-2.3-22b-distilled-Q4_K_S.gguf in the Unet Loader in the workflow with the Unsloth it just outputs a blurry picture. So I am having no luck as well. Hope someone can help with this.
@waterai might need to enable or disable the distilled lora.
@Zabaduadd an image to image loader and enable t2v. workflow needs an image but it will not be used when generating t2v
don't even bother with the gguf Q2 it's barely making coherent videos, but I guess the sound is somewhat acceptable so in very niche scenario if you only need sound... starting from Q4 it's okayish I guess the sweetspot is Q6 like most of the time
i have only 16gb vram so i guess at q5 is max i can use ?
@pink0909 With recent comfyUI managing memory far more efficiently, you might even be able to run the Q8 with zero problems (it also can unload on normal ram) so if you have 32 or 64 or more GB ram in addition you can try, but sure the Q5 should be zero problem, I have 24GB Vram and I use the Q5 UD usually, and I never seen an OOM so far with any LTX 2.3 even at 500+ frames, (I recommend the Q5 by unsloth, with the UD version, slightly higher size than usual Q5 but better quality)
I have 12gb vram and tried Q2, got very 'muddy' videos and can't solve it. Is is what you mean by 'dont even bother with q2...'?
@fakolonya yeah, q2 is basically 2 bit version of a 16 or 32 bit original model, too much loss, You probably can run Q4, and preferably the Q4 version made by unsloth (the UD version) in comfyUI unless you only have 16GB of ram in this case it might be a bit tight, because comfyUI can unload dynamically to ram to not go oom usually
@fakolonya Yeah Q2 is just too bad, Q3 UD might be decent enough, and Q4/Q5 sweet spot, yu should be able to run it, maybe reduce some resolution and frame lenght if you encounter oom.
@AiMetatron @DigitalPastel @taek75799 @darksidewalker @FX_FeiHou
the holy porn council
@darksidewalker How I'm waiting for your model, my friend)