You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
i am using HunyuanDiT-v1.2-Diffusers on Ascend NPU
import torch
import torch_npu
from torch_npu.contrib import transfer_to_npu
from diffusers import HunyuanDiTPipeline
pipe = HunyuanDiTPipeline.from_pretrained("/model/HunyuanDiT-v1.2-Diffusers", torch_dtype=torch.float16)
pipe.to("cuda")
# You may also use English prompt as HunyuanDiT supports both English and Chinese
# prompt = "An astronaut riding a horse"
prompt = "一个宇航员在骑马"
image = pipe(prompt).images[0]
when i choose fp16, the pic is all black, bf16 not good, like a mask
so, could u please support diffuser version for Ascend NPU, thanks!
The text was updated successfully, but these errors were encountered:
i am using HunyuanDiT-v1.2-Diffusers on Ascend NPU
when i choose fp16, the pic is all black, bf16 not good, like a mask
so, could u please support diffuser version for Ascend NPU, thanks!
The text was updated successfully, but these errors were encountered: