14 Commits

Include renames

Author	SHA1	Message	Date
wenjian	872011d8f1	Add ComfyUI node integration and fix compatibility issues ... - Add ComfyUI custom nodes: model loader, t2v, i2v, v2v - Fix kernels import: move to try block for graceful fallback when not installed - Fix diffusers compatibility: add fallback imports for HeliosLoraLoaderMixin, HeliosTransformer3DModel, HeliosScheduler, and apply_lora_scale - Fix infer_helios: cast num_blocks_per_group to int, add low_cpu_mem_usage - Add rh_config.json, model index compat, and deployment scripts Made-with: Cursor	2026-03-10 04:49:22 +08:00
SHYuanBest	d0183dd2bf	fix sample_block_noise	2026-03-08 09:01:22 +00:00
SHYuanBest	da848b52de	make style and quality	2026-03-08 08:56:22 +00:00
SHYuanBest	46a0c8874a	refacotr sample_block_noise	2026-03-08 08:54:01 +00:00
SHYuanBest	7903ec31b5	fix parallel inference for Helios-Mid & Helios-Distilled	2026-03-08 06:01:44 +00:00
SHYuanBest	f719fc5e91	make style and quality	2026-03-07 13:11:44 +00:00
SHYuanBest	947c347782	fix some typos	2026-03-07 13:09:23 +00:00
SHYuanBest	1d898bac20	small fix	2026-03-07 04:21:08 +00:00
SHYuanBest	1e40272194	add parallel inference	2026-03-06 13:35:49 +00:00
Shenghai Yuan	d273e9f9f5	Return full output from flash attention functions	2026-03-06 16:49:55 +08:00
Shenghai Yuan	164c39a5db	Convert tensors to float in optimized_scale function	2026-03-05 22:11:01 +08:00
Shenghai Yuan	7c57f907cb	Update transformer_helios.py	2026-03-05 20:16:47 +08:00
Shenghai Yuan	da901e7368	Expand _skip_layerwise_casting_patterns list	2026-03-05 20:16:19 +08:00
SHYuanBest	dd6a26ebaa	Initial commit	2026-03-04 03:31:47 +00:00