Downloads · 30 days
21
64% of all-time downloads
codemichaeld/hunyuan3D_2.1_fixed
hunyuan3D_2.1_fixed is a machine learning model from codemichaeld. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for diffusers.
- Source: https://huggingface.co/Comfy-Org/hunyuan3D2.1repackaged - Original File(s): hunyuan3dv2.1.safetensors - Original Format: safetensors - FP8 Format: E4M3FN - FP8 File: hunyuan3dv2.1-fp8-e4m3fn.safetensors
Downloads · 30 days
21
64% of all-time downloads
All-time downloads
33
Public
Repo size
3.7 GB
Likes
0
Public
Click a slice to open those files.
.safetensors3.7 GB · 100%
From the Hugging Face model README
https://huggingface.co/Comfy-Org/hunyuan3D_2.1_repackagedhunyuan_3d_v2.1.safetensorssafetensorsE4M3FNhunyuan_3d_v2.1-fp8-e4m3fn.safetensorsfrom safetensors.torch import load_file
import torch
# Load FP8 model
fp8_state = load_file("hunyuan_3d_v2.1-fp8-e4m3fn.safetensors")
# Convert tensors back to float32 for computation (auto-converted by PyTorch)
model.load_state_dict(fp8_state)
Note: FP8 tensors are automatically converted to float32 when loaded in PyTorch. Requires PyTorch ≥ 2.1 for FP8 support.