datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Sana-assetsprocessed_gpt_dataset_big
Dataset Card for "processed_gpt_dataset_big"
More Information needed
processed_gpt_dataset_medium
Dataset Card for "processed_gpt_dataset_medium"
More Information needed
processed_gpt_dataset_max
Dataset Card for "processed_gpt_dataset_max"
More Information needed
openve_r7s1_hi_s200openve_r7s1_lo_s200festival_audiosopenve_bernini_t1s1r5_eb24processed_pythia_dataset_2048
Dataset Card for "processed_pythia_dataset_2048"
More Information needed
openve_r5_t2s1r1_vmse_s100SANA-WM-Bench
SANA-WM-Bench
Minimal 80-scene, 60s SANA-WM benchmark release. It contains the 80 conditioning images, fixed public scene set, simple/hard 60s Sana-WM camera trajectories. Scene IDs are anonymized within each category as 001-020. It intentionally excludes 24s settings, non-Sana-WM export formats, baseline outputs, and generated videos.
Image Provenance
All conditioning images in images/ are AI-generated using Google's Nano Banana
(Gemini native image generation).… See the full description on the dataset page: https://huggingface.co/datasets/Efficient-Large-Model/SANA-WM-Bench.openve_r5_t2s1r1_xmse_s100openve_r5_t2s1r1_xmse_s200processed_llama_dataset_2048openve_r4_rcfg2_s100processed_bert_dataset
Dataset Card for "processed_bert_dataset"
More Information needed
openve_r4_t1r1s1_s200openve_r4_t2r1s1_s200refine-book-wiki_processed_llama_dataset_2048openve_r4_q4half_s200openve_q3_vcos_cfg1_step100openve_r4_t2r5s5_s100openve_r4_t1r5s1_s200IN1k256-AR-buckets-bfl16latents_dc-ae-f32c32-sana-1.0_recapPD12M-256px_dc-ae-f32c32-sana-1.0openve_r4_t2r5s1_s200openve_r4_t2r5s5_s200openve_r5_t2s1r1_vmse_s200openve_q4_vcos_tcfg2_halfbatchopenve_33f_fa_cfg1