Downloads · 30 days
1.6K
17% of all-time downloads
rzgar/ltx-2.3-22b-distilled-lora-384-1.1-n4w
ltx-2.3-22b-distilled-lora-384-1.1-n4w is a image-to-video model from rzgar. Use it for the image-to-video task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as apache-2.0.
<video controls width="1280" height="720" <source src="https://huggingface.co/rzgar/ltx-2.3-22b-distilled-lora-384-1.1-n4w/resolve/main/demo/demo.mp4" type="video/mp4" Your browser does not support the video tag. </video
Downloads · 30 days
1.6K
17% of all-time downloads
All-time downloads
9.6K
Public
Repo size
10.2 GB
Likes
2
Public
Click a slice to open those files.
.safetensors10.2 GB · 100%
From the Hugging Face model README
The official distilled LoRA more or less acts as a negative strength when stacked with N54W LoRAs, fighting against their appearance and animation characteristics. This lora is an attempt to solve that conflict. Instead of counteracting, it works with N54W LoRAs, improving motion and appearance to varying degrees.
| File | Size | Description |
|---|---|---|
| ltx-2.3-22b-distilled-lora-384-1.1_n4w.safetensors | 7.1 GB | same rank as the official |
| ltx-2.3-22b-distilled-lora-384-1.1_rank_128_n4w.safetensors | 2.4 GB | low VRAM, expect lower quality |
When stacked with N54W LoRAs listed on Civitai and used with prompts and input images that follow LTX-2.3 prompting guidelines, roughly 6 out of 10 videos are usable. Body deformity and broken animation can still occur, this is standard LTX-2.3 behaviour. Prompt deviation from the input image increases the error rate.
Download them in the Files & versions tab.