Open MnKnight1 opened 6 months ago
How about the results with rgb? The this is the video of textureless result.
How about the results with rgb? The this is the video of textureless result. I have also tried the “the pineapple”in the readme,but he result, like it, is a meaningless floating object.
df_ep0250_00_albedo_rgb.mp4
Is it due to environmental problems? but the program can run, the result is wrong, I do not understand why.
pip list
Package Version
--------------------------- ------------
absl-py 2.0.0
accelerate 0.25.0
aiofiles 23.2.1
aiohttp 3.9.1
aiosignal 1.3.1
annotated-types 0.6.0
antlr4-python3-runtime 4.9.3
anyio 3.7.1
async-timeout 4.0.3
attrs 23.1.0
beautifulsoup4 4.12.2
Brotli 1.0.9
cachetools 5.3.2
carvekit-colab 4.1.0
certifi 2023.11.17
cffi 1.15.0
chardet 4.0.0
charset-normalizer 2.0.4
click 8.1.7
clip 1.0
contourpy 1.1.1
cryptography 41.0.3
cycler 0.12.1
dearpygui 1.10.1
debugpy-run 1.8
diffusers 0.15.0
einops 0.7.0
exceptiongroup 1.2.0
fastapi 0.105.0
filelock 3.13.1
fonttools 4.46.0
frozenlist 1.4.0
fsspec 2023.12.2
ftfy 6.1.3
gdown 4.7.1
gmpy2 2.1.2
google-auth 2.25.2
google-auth-oauthlib 1.0.0
grpcio 1.60.0
h11 0.14.0
huggingface-hub 0.19.4
idna 3.4
imageio 2.33.1
imageio-ffmpeg 0.4.9
importlib-metadata 7.0.0
importlib-resources 6.1.1
Jinja2 3.1.2
joblib 1.3.2
kiwisolver 1.4.5
kornia 0.7.0
lightning-utilities 0.10.0
loguru 0.7.2
Markdown 3.5.1
markdown-it-py 3.0.0
MarkupSafe 2.1.1
matplotlib 3.7.4
mdurl 0.1.2
mkl-fft 1.3.1
mkl-random 1.2.2
mkl-service 2.4.0
mpmath 1.3.0
multidict 6.0.4
networkx 3.1
ninja 1.11.1.1
numpy 1.24.3
nvdiffrast 0.3.1
nvidia-cublas-cu12 12.1.3.1
nvidia-cuda-cupti-cu12 12.1.105
nvidia-cuda-nvrtc-cu12 12.1.105
nvidia-cuda-runtime-cu12 12.1.105
nvidia-cudnn-cu12 8.9.2.26
nvidia-cufft-cu12 11.0.2.54
nvidia-curand-cu12 10.3.2.106
nvidia-cusolver-cu12 11.4.5.107
nvidia-cusparse-cu12 12.1.0.106
nvidia-nccl-cu12 2.18.1
nvidia-nvjitlink-cu12 12.3.101
nvidia-nvtx-cu12 12.1.105
oauthlib 3.2.2
omegaconf 2.3.0
opencv-python 4.8.1.78
packaging 23.2
pandas 2.0.3
Pillow 10.0.1
pip 23.3.1
protobuf 4.25.1
psutil 5.9.6
pyasn1 0.5.1
pyasn1-modules 0.3.0
pycparser 2.21
pydantic 2.5.2
pydantic_core 2.14.5
Pygments 2.17.2
PyMCubes 0.1.4
pymeshlab 2022.2.post3
pyOpenSSL 23.2.0
pyparsing 3.1.1
PySocks 1.7.1
python-dateutil 2.8.2
python-multipart 0.0.6
pytorch-lightning 2.1.2
pytz 2023.3.post1
PyYAML 6.0.1
regex 2023.10.3
requests 2.31.0
requests-oauthlib 1.3.1
rich 13.7.0
rsa 4.9
safetensors 0.4.1
scikit-learn 1.3.2
scipy 1.10.1
sentencepiece 0.1.99
setuptools 68.0.0
six 1.16.0
sniffio 1.3.0
soupsieve 2.5
starlette 0.27.0
sympy 1.12
taming-transformers-rom1504 0.0.6
tensorboard 2.14.0
tensorboard-data-server 0.7.2
tensorboardX 2.6.2.2
threadpoolctl 3.2.0
timm 0.9.12
tokenizers 0.15.0
torch 1.12.1+cu113
torch-ema 0.3
torchaudio 2.0.2
torchmetrics 1.2.1
torchvision 0.13.1+cu113
tqdm 4.66.1
transformers 4.36.0
trimesh 4.0.5
triton 2.0.0
typing_extensions 4.7.1
tzdata 2023.3
urllib3 1.26.18
uvicorn 0.24.0.post1
wcwidth 0.2.12
Werkzeug 3.0.1
wheel 0.41.2
xatlas 0.0.8
yarl 1.9.4
zipp 3.17.0
(1) The lambda_entropy
is a critical parameter. How about setting --lambda_entropy 10?
(2) This prompt may be too hard for stable diffusion, maybe you can try a pineapple
first and figure out if a simple prompt can work.
yes,if I set lambda_entropy to 100,the pineapple can be generated. But some sentence like“Albert Einstein is playing the guitar” still can not be generated ,when lambda_entropy equals 100. Do you think this can be generated by adjusting the parameters? Because I see that some imaginative sentences in the paper can be generated, such as "Michelangelo style statue ofdog reading news on a cellphone"
In general, complex prompts require a more careful choice of the parameters. It is possible that this may be generated by adjusting the parameters or even by adding new regularization loss.
The commands I run are as follows:
But the output video seems meaningless. What's the reason?
df_ep0250_00_textureless_rgb.mp4