kwan3854 / ceb_econ Goto Github PK
View Code? Open in Web Editor NEWAI based all-in-one character generator Blender plug-in. This project contains unofficial updates for the CEB_ECON Blender add-on.
License: GNU General Public License v3.0
AI based all-in-one character generator Blender plug-in. This project contains unofficial updates for the CEB_ECON Blender add-on.
License: GNU General Public License v3.0
Maybe newbie question here, but after completing installation following the steps described (using CUDA 11.6 and vs tools 2019)and trying to generate a model using one of the test images provided, nothing happens. After using Blender's System Console an error message appears:
ImportError: cannot import name 'url_quote' from 'werkzeug.urls' (D:\Installed_Programs\ECON\ECON_38_env\lib\site-packages\werkzeug\urls.py)
I've been looking everywhere but I cannot find what is causing the issue.
Just tried following the tutorial and I am getting an issue at the last step downloading I also see that in the script you have your password hardcoded. Maybe I'm missing something.
Edit: I found the problem I had already registered for some of the other models with the smae user name but a different password. Changing my multiple mpg.de accounts to share the same password worked and I was able to download.
Hi, I've tried several times to go through install process in Blender but every times it blocks at the end of this steps:
Collecting torch==1.12.1+cu116 (from -r requirements. txt (line 24))
Is it related to installation of Python on my system?
I'm using Blender v.3.5.1
Hello, any chance there will be support coming for macOS or Linux? Thanks!
Hello, I came a cross this option "Install compiler"
it would be the sme file that I made available as Zip for people to use?
if it is, I think you need to tell about where people could get it, I didnt find information on the github.
Or, there is a better option.
I found tht the best is to inform the user to install visual studio build tools and CUDA sdk.
Installing both is more reliable and it will be usefull for more addons and software the user might want to install. while this compiling strategy that I used at that time was not scalable and had a lot of "trash" in it.
But, back on the question, this install compiler would be the same one that is available on the original code?
Thank you for your great work, when I did following CEB Econ Tutorial, when "Exucute" , the error message is as follows, how to solve it ?
File "F:\Econ-texture\ECON_39_env\lib\site-packages\numpy\lib\npyio.py", line 405, in load
fid = stack.enter_context(open(os_fspath(file), "rb"))
FileNotFoundError: [Errno 2] No such file or directory: 'C:\Users\Administrator\AppData\Roaming\Blender Foundation\Blender\3.6\scripts\addons\CEB_ECON\ECON\lib\dataset\../../data/smpl_related\smpl_data/smplx_faces.npy'
Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Roaming\Blender Foundation\Blender\3.6\scripts\addons\CEB_ECON\econ_blender.py", line 560, in execute
bpy.ops.wm.obj_import(filepath=final_obj[-1]) #import o ultimo
IndexError: list index out of range
Error: Python: Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Roaming\Blender Foundation\Blender\3.6\scripts\addons\CEB_ECON\econ_blender.py", line 560, in execute
bpy.ops.wm.obj_import(filepath=final_obj[-1]) #import o ultimo
IndexError: list index out of range
Hey, I was wondering what the hugging face tokens were required for? Would it be possible to create the model without them?
Is it only for texturing etc?
The reason I ask is because I noticed that CUDA is a requirement so I assumed ECON shipped with this to run locally but I may be wrong about that?
(ECON_38_env) C:\Users\Kendrick\AppData\Roaming\Blender Foundation\Blender\3.6\scripts\addons\CEB_ECON-main\ECON>python -m apps.infer -cfg ./configs/econ.yaml -in_dir ./examples -out_dir ./results Resume Normal Estimator from ./data/ckpt/normal.ckpt Resume IF-Net+ from ./data/ckpt/ifnet.ckpt Complete with IF-Nets+ (Implicit) SMPL-X estimate with PIXIE Dataset Size: 1 0%| | 0/1 [00:00<?, ?it/s]INFO: Created TensorFlow Lite XNNPACK delegate for CPU. Body Fitting -- normal: 0.015 | silhouette: 0.042 | joint: 0.056 | Total: 0.113| loose:0, occluded:0: 98%|▉| 49/50 [0 examples\PXL_20201106_052006014: 0%| | 0/1 [00:39<?, ?it/s] Traceback (most recent call last): File "runpy.py", line 194, in _run_module_as_main File "runpy.py", line 87, in _run_code File "C:\Users\Kendrick\AppData\Roaming\Blender Foundation\Blender\3.6\scripts\addons\CEB_ECON-main\ECON\apps\infer.py", line 343, in <module> get_optim_grid_image(per_loop_lst, None, nrow=N_body * 2, type="smpl") File "C:\Users\Kendrick\AppData\Roaming\Blender Foundation\Blender\3.6\scripts\addons\CEB_ECON-main\ECON\lib\dataset\mesh_util.py", line 668, in get_optim_grid_image grid_img = grid_img.resize((grid_img.size[0], grid_img.size[1]), Image.ANTIALIAS) AttributeError: module 'PIL.Image' has no attribute 'ANTIALIAS' Cannot read from OBJ file:'C:\Users\Kendrick\AppData\Roaming\Blender Foundation\Blender\3.6\scripts\addons\CEB_ECON-main\ECON\results\econ\obj\PXL_20201106_052006014_0_full.obj'. OBJ import of 'PXL_20201106_052006014_0_full.obj' took 0.2 ms
Looks like pillow changed at version 1.0.0 so we can either downgrade pillow or update the "CEB_ECON-main\ECON\lib\dataset\mesh_util.py" to use the new syntax.
pip install Pillow==9.5.0
or
line 668 in "CEB_ECON-main\ECON\lib\dataset\mesh_util.py"
grid_img = grid_img.resize((grid_img.size[0], grid_img.size[1]), Image.LANCZOS)
I just tested this second method and can confirm that it works.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.