nodes/HM-RunningHub-ComfyUI_RH_Helios
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

add group offloading

Browse Source
This commit is contained in:
SHYuanBest
2026-03-08 07:14:58 +00:00
parent c4ecf8e0d0
commit 5e5537c20f
11 changed files with 81 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/inference/helios-base_i2v.sh
+3
View File
@@ -16,6 +16,9 @@ CUDA_VISIBLE_DEVICES=0 python infer_helios.py \
--output_folder "./output_helios/helios-base"
# --enable_low_vram_mode \
# --group_offloading_type "leaf_level" \ # ["leaf_level", "block_level"]
# --num_blocks_per_group
# --use_cfg_zero_star \
# --use_zero_init \
# --zero_steps 1 \
scripts/inference/helios-base_t2v.sh
+3
View File
@@ -15,6 +15,9 @@ CUDA_VISIBLE_DEVICES=0 python infer_helios.py \
--output_folder "./output_helios/helios-base"
# --enable_low_vram_mode \
# --group_offloading_type "leaf_level" \ # ["leaf_level", "block_level"]
# --num_blocks_per_group
# --use_cfg_zero_star \
# --use_zero_init \
# --zero_steps 1 \
scripts/inference/helios-base_v2v.sh
+3
View File
@@ -16,6 +16,9 @@ CUDA_VISIBLE_DEVICES=0 python infer_helios.py \
--output_folder "./output_helios/helios-base"
# --enable_low_vram_mode \
# --group_offloading_type "leaf_level" \ # ["leaf_level", "block_level"]
# --num_blocks_per_group
# --use_cfg_zero_star \
# --use_zero_init \
# --zero_steps 1 \
scripts/inference/helios-distilled_i2v.sh
+3
View File
@@ -18,4 +18,7 @@ CUDA_VISIBLE_DEVICES=0 python infer_helios.py \
--output_folder "./output_helios/helios-distilled"
# --enable_low_vram_mode \
# --group_offloading_type "leaf_level" \ # ["leaf_level", "block_level"]
# --num_blocks_per_group
# --pyramid_num_inference_steps_list 1 1 1 \
scripts/inference/helios-distilled_t2v.sh
+3
View File
@@ -17,4 +17,7 @@ CUDA_VISIBLE_DEVICES=0 python infer_helios.py \
--output_folder "./output_helios/helios-distilled"
# --enable_low_vram_mode \
# --group_offloading_type "leaf_level" \ # ["leaf_level", "block_level"]
# --num_blocks_per_group
# --pyramid_num_inference_steps_list 1 1 1 \
scripts/inference/helios-distilled_v2v.sh
+3
View File
@@ -18,4 +18,7 @@ CUDA_VISIBLE_DEVICES=0 python infer_helios.py \
--output_folder "./output_helios/helios-distilled"
# --enable_low_vram_mode \
# --group_offloading_type "leaf_level" \ # ["leaf_level", "block_level"]
# --num_blocks_per_group
# --pyramid_num_inference_steps_list 1 1 1 \
scripts/inference/helios-mid_i2v.sh
+3
View File
@@ -20,4 +20,7 @@ CUDA_VISIBLE_DEVICES=0 python infer_helios.py \
--output_folder "./output_helios/helios-mid"
# --enable_low_vram_mode \
# --group_offloading_type "leaf_level" \ # ["leaf_level", "block_level"]
# --num_blocks_per_group
# --pyramid_num_inference_steps_list 17 17 17 \
scripts/inference/helios-mid_t2v.sh
+3
View File
@@ -19,4 +19,7 @@ CUDA_VISIBLE_DEVICES=0 python infer_helios.py \
--output_folder "./output_helios/helios-mid"
# --enable_low_vram_mode \
# --group_offloading_type "leaf_level" \ # ["leaf_level", "block_level"]
# --num_blocks_per_group
# --pyramid_num_inference_steps_list 17 17 17 \
scripts/inference/helios-mid_v2v.sh
+3
View File
@@ -20,4 +20,7 @@ CUDA_VISIBLE_DEVICES=0 python infer_helios.py \
--output_folder "./output_helios/helios-mid"
# --enable_low_vram_mode \
# --group_offloading_type "leaf_level" \ # ["leaf_level", "block_level"]
# --num_blocks_per_group
# --pyramid_num_inference_steps_list 17 17 17 \