Pavel Dostál
Pavel Dostal
About Me
I started as a CG-artist in 2002 on small projects(visualizations for public departments) in 2004 I became 3d artist for Fanatic games studio(game models, rigging, optimization) which was my big career jump. Since then I've been producing game models and resources to many projects including Mafia(Il... more
I started as a CG-artist in 2002 on small projects(visualizations for public departments) in 2004 I became 3d artist for Fanatic games studio(game models, rigging, optimization) which was my big career jump. Since then I've been producing game models and resources to many projects including Mafia(Illusion softworks), Overkill 3 (Craneballs studios), World of tanks(Wargaming). Lately I am concentrating on creating interior&exterior resources for visualizations and games for Unreal engine. less
専門知識
Freelancer
業界:
Gamedev
Houdini Engine
Availability
Not Specified
My Gallery
Recent Forum Posts
Auto-thumbnail generator for HIP files 2025年7月11日5:51
Hi everyone,
I'd like to share a small but useful tool I've built for Houdini: an automatic thumbnail generator that creates a PNG preview of your scene every time you save your .hip file.
🔧 What it does:
On save, it captures a viewport screenshot and saves it as
YourScene_thumbnail.png next to your .hip file.
It works with any Houdini project — no setup required.
Perfect for visual version tracking, asset libraries, or Perforce integration.
🛠 How to install:
Just drop the script into your scripts/456.py (or add to an existing one).
Detailed steps are included in the attached README.
This was created as part of a workflow that integrates Houdini with P4One (Perforce GUI), where visual thumbnails for .hip or .fbx files are missing — but it's generally useful even without Perforce.
Let me know if you have any suggestions, questions, or ideas for improvements!
Cheers,
Pavel Dostal
I'd like to share a small but useful tool I've built for Houdini: an automatic thumbnail generator that creates a PNG preview of your scene every time you save your .hip file.
🔧 What it does:
On save, it captures a viewport screenshot and saves it as
YourScene_thumbnail.png next to your .hip file.
It works with any Houdini project — no setup required.
Perfect for visual version tracking, asset libraries, or Perforce integration.
🛠 How to install:
Just drop the script into your scripts/456.py (or add to an existing one).
Detailed steps are included in the attached README.
This was created as part of a workflow that integrates Houdini with P4One (Perforce GUI), where visual thumbnails for .hip or .fbx files are missing — but it's generally useful even without Perforce.
Let me know if you have any suggestions, questions, or ideas for improvements!
Cheers,
Pavel Dostal
Integrating ComfyUI AI-generated concepts into Houdini 2025年6月10日2:12
Hi everyone,
I’m currently building a pipeline where I generate concept images (vehicles, terrain, etc.) using ComfyUI (Stable Diffusion) and then feed them into Houdini for further processing – either as reference or for semi-automated geometry creation (through ML-enhanced Top Networks, depth maps, segmentation, etc.).
The idea is to have a semi-automatic flow:
Input prompt in ComfyUI → image generated
Houdini picks latest image from directory (using COP2 or TOPs)
(Later) Use ML to extract depth / structure → create procedural model or layout
Final output goes to Unreal Engine as asset/environment
🔧 I’m still in the early phase, so I’m experimenting with:
integrating ONNX inference directly inside Houdini
controlling generation from within Houdini (via Python)
proceduralizing based on 2D-to-3D logic or tagged structure
I'm wondering:
Has anyone built something similar (AI > Houdini > UE pipeline)?
What would you recommend for handling image-driven procedural generation?
Any tips for integrating ComfyUI output dynamically into COP2 / TOPs networks?
Here’s a screenshot of the current system in action (ComfyUI + Houdini preview):
Thanks a lot – I’d love to share more as this progresses!
Pavel
https://www.novusion.eu/ [www.novusion.eu] | https://www.artstation.com/infinitex/ [www.artstation.com]
I’m currently building a pipeline where I generate concept images (vehicles, terrain, etc.) using ComfyUI (Stable Diffusion) and then feed them into Houdini for further processing – either as reference or for semi-automated geometry creation (through ML-enhanced Top Networks, depth maps, segmentation, etc.).
The idea is to have a semi-automatic flow:
Input prompt in ComfyUI → image generated
Houdini picks latest image from directory (using COP2 or TOPs)
(Later) Use ML to extract depth / structure → create procedural model or layout
Final output goes to Unreal Engine as asset/environment
🔧 I’m still in the early phase, so I’m experimenting with:
integrating ONNX inference directly inside Houdini
controlling generation from within Houdini (via Python)
proceduralizing based on 2D-to-3D logic or tagged structure
I'm wondering:
Has anyone built something similar (AI > Houdini > UE pipeline)?
What would you recommend for handling image-driven procedural generation?
Any tips for integrating ComfyUI output dynamically into COP2 / TOPs networks?
Here’s a screenshot of the current system in action (ComfyUI + Houdini preview):
Thanks a lot – I’d love to share more as this progresses!
Pavel
https://www.novusion.eu/ [www.novusion.eu] | https://www.artstation.com/infinitex/ [www.artstation.com]
How to set relative path to hou.hipfile.load 2020年3月4日16:50
solved