showlab
Why are the inference results different from the results you posted?
Hello author, I used the weights you provided for intervention. The seed is the same as the one you set. Why are the results I got different from the results you published? I would be grateful if you could answer my doubts. .
There are two possible reasons. 1) Our torch version is different, which means that the same random seed may generate different noises. 2) The released model has been updated later. I recommend you use the demo in huggingface space, where the models are updated to the newest version.
I'm very glad that you can reply to my message. I tried changing the torch version, but the result is still the same. The following is the environment I configured. I hope you can take a look:
# packages in environment at D:\anaconda\envs\motion1:
# Name Version Build Channel
absl-py 2.1.0 pypi_0 pypi
accelerate 0.18.0 pypi_0 pypi
antlr4-python3-runtime 4.9.3 pypi_0 pypi
appdirs 1.4.4 pypi_0 pypi
attrs 23.2.0 pypi_0 pypi
ca-certificates 2024.3.11 haa95532_0 defaults
certifi 2024.2.2 pypi_0 pypi
cffi 1.16.0 pypi_0 pypi
charset-normalizer 3.3.2 pypi_0 pypi
click 8.1.7 pypi_0 pypi
colorama 0.4.6 pypi_0 pypi
contourpy 1.1.1 pypi_0 pypi
cycler 0.12.1 pypi_0 pypi
decord 0.6.0 pypi_0 pypi
deepspeed 0.3.16 pypi_0 pypi
diffusers 0.18.0 pypi_0 pypi
docker-pycreds 0.4.0 pypi_0 pypi
einops 0.7.0 pypi_0 pypi
filelock 3.13.3 pypi_0 pypi
fire 0.6.0 pypi_0 pypi
flatbuffers 24.3.25 pypi_0 pypi
fonttools 4.51.0 pypi_0 pypi
fsspec 2024.3.1 pypi_0 pypi
ftfy 6.2.0 pypi_0 pypi
git 2.44.0 h57928b3_0 defaults
gitdb 4.0.11 pypi_0 pypi
gitpython 3.1.43 pypi_0 pypi
huggingface-hub 0.16.4 pypi_0 pypi
idna 3.6 pypi_0 pypi
imageio 2.33.0 pypi_0 pypi
imageio-ffmpeg 0.4.9 pypi_0 pypi
importlib-metadata 7.1.0 pypi_0 pypi
importlib-resources 6.4.0 pypi_0 pypi
jax 0.4.13 pypi_0 pypi
jinja2 3.1.3 pypi_0 pypi
kiwisolver 1.4.5 pypi_0 pypi
libffi 3.4.4 hd77b12b_0 defaults
libsqlite 3.45.2 hcfcfb64_0 defaults
lora-diffusion 0.1.7 pypi_0 pypi
loralib 0.1.0 pypi_0 pypi
markupsafe 2.1.5 pypi_0 pypi
matplotlib 3.7.5 pypi_0 pypi
mediapipe 0.10.11 pypi_0 pypi
ml-dtypes 0.2.0 pypi_0 pypi
mpmath 1.3.0 pypi_0 pypi
mypy-extensions 1.0.0 pypi_0 pypi
networkx 3.1 pypi_0 pypi
ninja 1.11.1.1 pypi_0 pypi
numpy 1.24.0 pypi_0 pypi
omegaconf 2.3.0 pypi_0 pypi
opencv-contrib-python 4.9.0.80 pypi_0 pypi
opencv-python 4.8.0.74 pypi_0 pypi
openssl 3.0.13 h2bbff1b_0 defaults
opt-einsum 3.3.0 pypi_0 pypi
packaging 24.0 pypi_0 pypi
pandas 2.0.3 pypi_0 pypi
pillow 10.3.0 pypi_0 pypi
pip 24.0 pyhd8ed1ab_0 defaults
protobuf 3.20.3 pypi_0 pypi
psutil 5.9.8 pypi_0 pypi
pycparser 2.22 pypi_0 pypi
pyparsing 3.1.2 pypi_0 pypi
pyre-extensions 0.0.29 pypi_0 pypi
python 3.8.19 h1aa4202_0 defaults
python-dateutil 2.9.0.post0 pypi_0 pypi
pytz 2024.1 pypi_0 pypi
pyyaml 6.0.1 pypi_0 pypi
regex 2023.12.25 pypi_0 pypi
requests 2.31.0 pypi_0 pypi
safetensors 0.4.2 pypi_0 pypi
scipy 1.10.1 pypi_0 pypi
sentry-sdk 1.44.1 pypi_0 pypi
setproctitle 1.3.3 pypi_0 pypi
setuptools 65.6.3 pyhd8ed1ab_0 defaults
six 1.16.0 pypi_0 pypi
smmap 5.0.1 pypi_0 pypi
sounddevice 0.4.6 pypi_0 pypi
sqlite 3.45.2 hcfcfb64_0 defaults
sympy 1.12 pypi_0 pypi
tensorboardx 1.8 pypi_0 pypi
termcolor 2.4.0 pypi_0 pypi
tokenizers 0.13.3 pypi_0 pypi
torch 2.0.1+cu118 pypi_0 pypi
torchaudio 2.0.2+cu118 pypi_0 pypi
torchvision 0.15.2+cu118 pypi_0 pypi
tqdm 4.65.0 pypi_0 pypi
transformers 4.27.4 pypi_0 pypi
typing-extensions 4.11.0 pypi_0 pypi
typing-inspect 0.9.0 pypi_0 pypi
tzdata 2024.1 pypi_0 pypi
ucrt 10.0.22621.0 h57928b3_0 defaults
urllib3 2.2.1 pypi_0 pypi
vc 14.3 hcf57466_18 defaults
vc14_runtime 14.38.33130 h82b7239_18 defaults
vs2015_runtime 14.38.33130 hcb4865c_18 defaults
wandb 0.16.6 pypi_0 pypi
wcwidth 0.2.13 pypi_0 pypi
wheel 0.41.2 py38haa95532_0 defaults
xformers 0.0.20 pypi_0 pypi
zipp 3.18.1 pypi_0 pypi
This is the command I used.
python MotionDirector_inference.py --model ./models/zeroscope_v2_576w --prompt "A panda is riding a bicycle in a garden." --checkpoint_folder ./outputs2/train/riding_bicycle/ --checkpoint_index 300 --noise_prior 0. --seed 2178639
Here, "A panda is riding a bicycle in a garden." still doesn't work very well. Looking forward to your answer, I will be grateful if you can solve my problem
+1. "A panda is riding a bicycle in a garden." does not work weel too.
+1，I cannot reproduce results as beautiful as the author's.Have you solved this problem?
Sorry for the late reply. I checked the results you provided and found that only the result of the "panda riding a bicycle" is abnormal while other results are the same as the results I posted.
After carefully checking the results, I found that I confused the random seed used for different version models. I found that the seed 2178639 is used by the newer model in the hugging space https://huggingface.co/spaces/ruizhaocv/MotionDirector.
In the demo, input the text prompt with the same seed, and I get the same results as follows. I recommend you to go to the huggingface space to have a try.