pottokao
/

H3-RotNVFP4-ComfyUI-Loader

Model card Files Files and versions

H3-RotNVFP4-ComfyUI-Loader

57.1 kB

Ctrl+K

Ctrl+K

1 contributor

History: 8 commits

pottokao's picture

Add workflow setup notes (files, node deps, sampler rationale)

74c7c6d verified 30 days ago

.gitattributes

1.52 kB
initial commit about 2 months ago
METHODOLOGY.md

8.18 kB
METHODOLOGY: measured max clip length per config (dense 310f/124f; VSA 68f/OOM) about 2 months ago
README.md

2.83 kB
H3RotNVFP4Loader node + methodology (device-bug fixed) about 2 months ago
WORKFLOW.md

1.7 kB
Add workflow setup notes (files, node deps, sampler rationale) 30 days ago
__init__.py

131 Bytes
H3RotNVFP4Loader node + methodology (device-bug fixed) about 2 months ago
nodes.py

38.9 kB
loader: build fp4 blocks directly (no ~72GB bf16 load transient); --gpu-only loads in 4s @10.57GB peak, DiT resident 12.777GB zero offload; output bit-identical (SSIM 1.0). Device-bug fix retained. about 2 months ago
requirements.txt

835 Bytes
H3RotNVFP4Loader node + methodology (device-bug fixed) about 2 months ago
workflow.json

2.91 kB
Add the workflow.json the README promised (h3_fasth3_T1.safetensors, 4 steps, euler) 30 days ago