Image-to-3D
ONNX
GGUF
pbr
texture
normal-map
3d
rigging
qtmesheditor
qtmesh
qtmesh-cloud
conversational
Instructions to use fernandotonon/QtMeshEditor-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use fernandotonon/QtMeshEditor-models with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="fernandotonon/QtMeshEditor-models", filename="caption/SmolVLM-500M-Instruct-Q8_0.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use fernandotonon/QtMeshEditor-models with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf fernandotonon/QtMeshEditor-models:Q8_0 # Run inference directly in the terminal: llama cli -hf fernandotonon/QtMeshEditor-models:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf fernandotonon/QtMeshEditor-models:Q8_0 # Run inference directly in the terminal: llama cli -hf fernandotonon/QtMeshEditor-models:Q8_0
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf fernandotonon/QtMeshEditor-models:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf fernandotonon/QtMeshEditor-models:Q8_0
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf fernandotonon/QtMeshEditor-models:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf fernandotonon/QtMeshEditor-models:Q8_0
Use Docker
docker model run hf.co/fernandotonon/QtMeshEditor-models:Q8_0
- LM Studio
- Jan
- Ollama
How to use fernandotonon/QtMeshEditor-models with Ollama:
ollama run hf.co/fernandotonon/QtMeshEditor-models:Q8_0
- Unsloth Studio
How to use fernandotonon/QtMeshEditor-models with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for fernandotonon/QtMeshEditor-models to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for fernandotonon/QtMeshEditor-models to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for fernandotonon/QtMeshEditor-models to start chatting
- Atomic Chat new
- Docker Model Runner
How to use fernandotonon/QtMeshEditor-models with Docker Model Runner:
docker model run hf.co/fernandotonon/QtMeshEditor-models:Q8_0
- Lemonade
How to use fernandotonon/QtMeshEditor-models with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull fernandotonon/QtMeshEditor-models:Q8_0
Run and chat with the model
lemonade run user.QtMeshEditor-models-Q8_0
List all available models
lemonade list
Add CC0 PBRify ONNX models (#404)
Browse files- 1x-PBRify_Height.onnx +3 -0
- 1x-PBRify_NormalV3.onnx +3 -0
- 1x-PBRify_RoughnessV2.onnx +3 -0
- README.md +33 -0
1x-PBRify_Height.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b14afd583148cb5b0a554bf86a009b6a898aadc00d213aa3ec2544e17c835f5
|
| 3 |
+
size 1640690
|
1x-PBRify_NormalV3.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19d78f555f994219e2692876ab0fb6c3e4382503952dbe72d74db89d24870ba4
|
| 3 |
+
size 1640690
|
1x-PBRify_RoughnessV2.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a8de1bbeab70df8b2550bdc11fddd5a315a12eeb47d561ce55b38551ea52131
|
| 3 |
+
size 1640690
|
README.md
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc0-1.0
|
| 3 |
+
tags:
|
| 4 |
+
- onnx
|
| 5 |
+
- pbr
|
| 6 |
+
- texture
|
| 7 |
+
- normal-map
|
| 8 |
+
- qtmesheditor
|
| 9 |
+
library_name: onnx
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# QtMeshEditor — AI models
|
| 13 |
+
|
| 14 |
+
ONNX models used by [QtMeshEditor](https://github.com/fernandotonon/QtMeshEditor)'s
|
| 15 |
+
AI-assisted authoring features.
|
| 16 |
+
|
| 17 |
+
## PBR map synthesis (issue #404)
|
| 18 |
+
|
| 19 |
+
`1x-PBRify_NormalV3.onnx`, `1x-PBRify_RoughnessV2.onnx`, `1x-PBRify_Height.onnx`
|
| 20 |
+
generate tangent-space normal / roughness / height maps from a single albedo
|
| 21 |
+
(diffuse) texture.
|
| 22 |
+
|
| 23 |
+
These are **ONNX re-exports** of the CC0 SPAN models from
|
| 24 |
+
**[Kim2091/PBRify_Remix](https://github.com/Kim2091/PBRify_Remix)** (LICENSE:
|
| 25 |
+
CC0-1.0), trained on CC0 content from ambientCG / Poly Haven. Converted with
|
| 26 |
+
`scripts/export-pbrify-onnx.py` in the QtMeshEditor repo (spandrel +
|
| 27 |
+
`torch.onnx.export`, opset 18). All credit for the weights goes to Kim2091.
|
| 28 |
+
|
| 29 |
+
- **License:** CC0-1.0 (public domain), same as the source models.
|
| 30 |
+
- **I/O:** 1×3×H×W float NCHW in `[0,1]` → 1×3×H×W out (normal as RGB;
|
| 31 |
+
roughness/height as RGB, consumed as luminance). Dynamic H/W.
|
| 32 |
+
|
| 33 |
+
QtMeshEditor downloads these on first use into `<AppData>/ai_models/pbr/`.
|