Instructions to use TenStrip/LTX2.3-10Eros with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TenStrip/LTX2.3-10Eros with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TenStrip/LTX2.3-10Eros", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
How to train on 1.4
I just saw in the model card that 1.4 is set up to be trained on into a base. how do we do that? can anyone point us (the community) in the right direction? any tutorials or anything?
awesome! thank you, TenStrip.
I'd like to know too still figuring out how I'm gonna set a runpod template up.
I'd like to know too still figuring out how I'm gonna set a runpod template up.
Ah, gotcha. Understood. There is a new model on civit called "SexGod PinkCherry LTX 2.3 NSFW Checkpoint". Perhaps you could reach out to him/her and brainstorm? I tested that model and it's good too.
I'd like to know too still figuring out how I'm gonna set a runpod template up.
Ah, gotcha. Understood. There is a new model on civit called "SexGod PinkCherry LTX 2.3 NSFW Checkpoint". Perhaps you could reach out to him/her and brainstorm? I tested that model and it's good too.
He's just merging sulphur and reasoning loras into the base checkpoint, and recently took my DMD extraction and acted like it's his new thing. It also looks like he's now hitting those sulphur issues that I already fixed and one of the reasons I won't share scripts or methods now. None of that is his own training just like I haven't trained this one yet, but I will now.
I'd like to know too still figuring out how I'm gonna set a runpod template up.
Ah, gotcha. Understood. There is a new model on civit called "SexGod PinkCherry LTX 2.3 NSFW Checkpoint". Perhaps you could reach out to him/her and brainstorm? I tested that model and it's good too.
He's just merging sulphur and reasoning loras into the base checkpoint, and recently took my DMD extraction and acted like it's his new thing. It also looks like he's now hitting those sulphur issues that I already fixed and one of the reasons I won't share scripts or methods now. None of that is his own training just like I haven't trained this one yet, but I will now.
OH shit, I didn't know that. what a chump. I would like to attempt my own training on top of 1.4 when it's possible. keep rockin!
"and recently took my DMD extraction and acted like it's his new thing"
With respect, I did not. I have not used any Eros loras or v1.4 etc of your loras (im sure they are wonderful though), I dont even know what your DMD lora does. I have my own training pipeline, and dataset. I was one of the first to post a nsfw nudity lora on civitai when LTX 2.0 was first released. Again, not trying to take anything away from what you are doing as it looks like you're doing great things for the community. We are on the same team, no need to fight.