codemichaeld/wan_1.3b_v4-fp8

FP8 Model Conversion

• Source: https://huggingface.co/Kijai/WanVideo_comfy/OneToAllAnimation
• Original File(s): Wan21-OneToAllAnimation_1_3B_v2_fp16.safetensors
• Original Format: safetensors
• FP8 Format: E5M2
• FP8 File: Wan21-OneToAllAnimation_1_3B_v2_fp16-fp8-e5m2.safetensors

Usage

from safetensors.torch import load_file
import torch

# Load FP8 model
fp8_state = load_file("Wan21-OneToAllAnimation_1_3B_v2_fp16-fp8-e5m2.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.

Statistics

• Total tensors: 1329
• Converted to FP8: 1329
• Skipped (non-float): 0