hao-ai-lab-FastVideo

kandinsky6_sr

[feat] Add external-launcher executor for multi-node inference (#1746 )

2026-10-07 04:46:26 -07:00

_denoising_fixtures.py

[misc] Move test-suite environment access into the registry and allowlists (#1898 )

2026-09-30 00:15:39 -07:00

kandinsky6_ti2va_tiny.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_causal_kv_cache_offsets.py

[bugfix] Fix Ulysses sequence-parallel crash in self-forcing causal Wan DiT (#1627 )

2026-10-07 03:29:22 -07:00

test_cfg_gating.py

[misc] Move test-suite environment access into the registry and allowlists (#1898 )

2026-09-30 00:15:39 -07:00

test_denoising_cudagraph_step.py

[bugfix] Make torch.compile reduce-overhead work in the shared denoising loop (Wan T2V) (#2047 )

2026-11-07 23:55:36 +00:00

test_external_launcher_output_ownership.py

[feat] Add external-launcher executor for multi-node inference (#1746 )

2026-10-07 04:46:26 -07:00

test_hy15_image_encoding_stage.py

[bugfix]: condition HunyuanVideo 1.5 i2v on the reference image (#1693 )

2026-10-07 01:36:35 -07:00

test_image_vae_encoding.py

[bugfix]: normalize uint8 pil_image in I2V VAE encoding (#1249 )

2026-04-24 09:16:01 +00:00

test_input_validation.py

[bugfix] Reject missing CFG negative conditioning during input validation (#2011 )

2026-10-27 08:45:21 +00:00

test_kandinsky5_attention_backend_guard.py

[bugfix] Fix environment-variable bugs in LTX-2 debug logging, HF token lookup, and attention backend reads (#1895 )

2026-09-29 11:48:31 -07:00

test_kandinsky5_dmd_stage_backend_engages.py

[misc] Move test-suite environment access into the registry and allowlists (#1898 )

2026-09-30 00:15:39 -07:00

test_kandinsky5_target_dtype.py

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702 )

2026-08-08 22:24:17 -07:00

test_kandinsky6_arch_config.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_kandinsky6_audio_decoding.py

[feat] Add external-launcher executor for multi-node inference (#1746 )

2026-10-07 04:46:26 -07:00

test_kandinsky6_audio_latent_duration.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_kandinsky6_cfg_resolution.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_kandinsky6_denoising_precision.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_kandinsky6_empty_prompt.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_kandinsky6_image_conditioning.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_kandinsky6_latent_preparation.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_kandinsky6_max_sequence_length.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_kandinsky6_parameter_dtype.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_kandinsky6_piflow_guidance.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_kandinsky6_registry.py

[feat]: Kandinsky 6 Lite: register the 3.2B checkpoints and add docs + cookbook recipes (#1927 )

2026-10-06 17:09:53 -07:00

test_kandinsky6_target_dtype.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_kandinsky6_ti2va_transformer.py

[feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924 )

2026-10-06 10:50:17 -07:00

test_lazy_module_load.py

[new-model] Add Pika H3 Flex inference support (#2038 )

2026-11-01 22:33:10 -08:00

test_ltx2_refine_upsampler_resolve.py

[docs] Add LTX-2.3 distilled inference run configs (t2v/i2v × 5+2/8+3 × resolutions) (#1568 )

2026-07-09 18:53:12 +00:00

test_magi_human_sr_latent_preparation.py

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702 )

2026-08-08 22:24:17 -07:00

test_minimax_h3_consumer_regressions.py

[feat]: FastH3 OmniRef inference on consumer devices (RTX 5090 / PRO 6000 / DGX Spark / 4090) (#1980 )

2026-10-19 14:57:36 -07:00

test_minimax_h3_continuation.py

[feat] MiniMax-H3 Ref2VA: continue an earlier video from its last frames (#2001 )

2026-11-05 01:24:11 +00:00

test_minimax_h3_distilled_schedule.py

[new-model] Add Pika H3 Flex inference support (#2038 )

2026-11-01 22:33:10 -08:00

test_minimax_h3_encoding_offload.py

[misc] Move test-suite environment access into the registry and allowlists (#1898 )

2026-09-30 00:15:39 -07:00

test_minimax_h3_input_preparation.py

[bugfix]: allow MiniMax H3 frame padding at the 15-second limit

2026-09-14 16:54:41 -07:00

test_minimax_h3_pdd_contract.py

[feat] Add H3 PDD/DMPDD training and packed Ref2VA preprocessing (#1984 )

2026-10-20 11:15:57 -07:00

test_minimax_h3_pdd_denoising.py

[feat] FastH3 Ref2VA PDD inference with reference-video VSA sparsity (#1907 )

2026-10-02 11:28:07 -07:00

test_minimax_h3_ref2va_memo.py

[perf] FastH3 OmniRef: lossless speed-ups behind default-off switches (#1930 )

2026-10-07 15:35:37 -07:00

test_minimax_h3_sequential_start.py

[feat]: FastH3 OmniRef inference on consumer devices (RTX 5090 / PRO 6000 / DGX Spark / 4090) (#1980 )

2026-10-19 14:57:36 -07:00

test_minimax_h3_vae_streaming.py

[perf] MiniMax H3: faster FP4 attention padding, uint8 VAE pixel path and cuDNN FP4 GEMMs (#2046 )

2026-11-01 22:23:10 -08:00

test_minimax_h3_vsa_guard.py

[feat]: FastH3 on single RTX GPUs (#1919 )

2026-10-06 11:37:01 -07:00

test_pika_h3_flex_geometry.py

[new-model] Add Pika H3 Flex inference support (#2038 )

2026-11-01 22:33:10 -08:00

test_pika_h3_flex_lazy_adapter.py

[new-model] Add Pika H3 Flex inference support (#2038 )

2026-11-01 22:33:10 -08:00

test_pika_h3_flex_request_constraints.py

[new-model] Add Pika H3 Flex inference support (#2038 )

2026-11-01 22:33:10 -08:00

test_pika_h3_flex_scheduler.py

[new-model] Add Pika H3 Flex inference support (#2038 )

2026-11-01 22:33:10 -08:00

test_qwen_image21_stages.py

[new-model] Add initial Qwen-Image-2.1 inference (#1918 )

2026-10-25 17:28:49 +00:00

test_text_encoding.py

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702 )

2026-08-08 22:24:17 -07:00

test_wan_causal_denoising.py

[misc] Move test-suite environment access into the registry and allowlists (#1898 )

2026-09-30 00:15:39 -07:00

test_wan_denoising.py

[misc] Move test-suite environment access into the registry and allowlists (#1898 )

2026-09-30 00:15:39 -07:00

test_wan_dmd_denoising.py

[misc] Move test-suite environment access into the registry and allowlists (#1898 )

2026-09-30 00:15:39 -07:00

test_wan_pipeline_wiring.py

[misc] Remove DreamX World, HunyuanGameCraft, GLM-Image, LongCat, TurboDiffusion, and Z-Image (#1926 )

2026-10-14 23:16:32 -07:00