datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
animeshooter-multishot-iclora
AnimeShooter → LTX-2.3 IC-LoRA multi-shot training pairs
276 reference-guided multi-shot training pairs derived from the
AnimeShooter dataset
(Qiu et al., 2025, arXiv:2506.03126), formatted for the
ltx-community/ltx2-lora-trainer
Space in IC-LoRA mode.
Each sample is:
videos/<id>.mp4 — a ~5.2s clip (126 frames, H.264) spanning 2–3 consecutive shots
(real cuts inside the clip) from an animated YouTube video listed in AnimeShooter.
videos/<id>_reference.png — a 768×512… See the full description on the dataset page: https://huggingface.co/datasets/linoyts/animeshooter-multishot-iclora.LTX2.3-22B_IC-LoRA-CrossView-Prompt-Dataset
CrossView Prompt Dataset
The training dataset behind the
CrossView Prompt IC-LoRA
for LTX-Video 2.3 — a "virtual second camera" adapter that re-renders a scene
from a new viewpoint described by a short prompt.
Each sample is a pair of static-camera clips of the same scene (a reference
view and a target view) plus a camera-delta caption describing how the
target camera differs from the reference.
Contents
clips/<scene>/<cam>.mp4 # 504 unique clips, native… See the full description on the dataset page: https://huggingface.co/datasets/Cseti/LTX2.3-22B_IC-LoRA-CrossView-Prompt-Dataset.ltx-2.5-ic-lora-cartoon-dataset
LTX-2.5 IC-LoRA cartoon dataset — 27 paired clips
Training data for
Baberg/ltx-2.5-22b-ic-lora-cel-character.
A fully synthetic dataset, created from scratch — nothing filmed or scraped. Cinematic
live-action clips were generated, each built around one clearly identifiable central character.
For each clip the first frame was extracted, the central character in it was replaced with a 2D
cel-animated version of the same character in the same pose and framing, and the clip was then… See the full description on the dataset page: https://huggingface.co/datasets/Baberg/ltx-2.5-ic-lora-cartoon-dataset.LTX_Upscale_IC-Loraltx2-ic-lora-test-data
LTX-2.3 IC-LoRA test dataset
3 clips + Canny *_reference controls, in trainer dataset.json format (media_path + caption + reference_video). For testing the LTX-2 LoRA Trainer Space's Hub-dataset path.
LTX-IC-LoraLTX2.3-22B_IC-LoRA-CrossView-Prompt-Dataset
CrossView Prompt Dataset
The training dataset behind the
CrossView Prompt IC-LoRA
for LTX-Video 2.3 — a "virtual second camera" adapter that re-renders a scene
from a new viewpoint described by a short prompt.
Each sample is a pair of static-camera clips of the same scene (a reference
view and a target view) plus a camera-delta caption describing how the
target camera differs from the reference.
Contents
clips/<scene>/<cam>.mp4 # 504 unique clips, native… See the full description on the dataset page: https://huggingface.co/datasets/inaganopresley/LTX2.3-22B_IC-LoRA-CrossView-Prompt-Dataset.