Add stable-fast-3d (#2388)

CVS-151527

.ci/ignore_treon_docker.txt

@@ -80,3 +80,4 @@ notebooks/stable-audio/stable-audio.ipynb
 notebooks/internvl2/internvl2.ipynb
 notebooks/qwen2-vl/qwen2-vl.ipynb
 notebooks/qwen2-audio/qwen2-audio.ipynb
+notebooks/stable-fast-3d/stable-fast-3d.ipynb

.ci/skipped_nightly.yml

@@ -6,4 +6,10 @@
 - notebook: notebooks/gpu-device/gpu-device.ipynb
   skips:
     - device:
-        - cpu
+        - cpu
+- notebook: notebooks/stable-fast-3d/stable-fast-3d.ipynb
+  skips:
+    - python:
+      - '3.8'
+    - os:
+        - macos-12

.ci/skipped_notebooks.yml

@@ -580,4 +580,10 @@
         - macos-12
         - ubuntu-20.04
         - ubuntu-22.04
-        - windows-2019
+        - windows-2019
+- notebook: notebooks/stable-fast-3d/stable-fast-3d.ipynb
+  skips:
+    - python:
+      - '3.8'
+    - os:
+        - macos-12

.ci/spellcheck/.pyspelling.wordlist.txt

@@ -97,6 +97,7 @@ classname
 ClassProbabilityMap
 CLI
 cli
+ClipBasedHeadEstimator
 CLIP's
 codebase
 codebook
@@ -196,6 +197,7 @@ diarization
 Diffusers
 diffusers
 dimensionality
+DINOv
 Distil
 distil
 DistilBERT
@@ -233,6 +235,7 @@ editability
 EfficientNet
 EfficientSAM
 EfficientSAMs
+embedder
 Embedder
 embeddings
 EnCodec
@@ -366,6 +369,7 @@ intervaling
 im
 img
 ip
+ir
 IRs
 iteratively
 JFLEG
@@ -422,6 +426,7 @@ LeViT
 LibriSpeech
 librispeech
 Lim
+LinearCameraEmbedder
 Liu
 LLama
 LLaMa
@@ -452,6 +457,8 @@ Mapillary
 Markovian
 Martyniuk
 maskrcnn
+MaterialMLP
+MaterialNet
 mathbf
 MathVista
 MatMul
@@ -620,12 +627,14 @@ Piotr
 Pipelining
 PixArt
 PIXART
+PixelShuffleUpsampleNetwork
 pixelwise
 PIL
 PNDM
 png
 Pointilism
 PointNet
+pos
 Postfuse
 postprocess
 postprocesses
@@ -874,13 +883,17 @@ TorchScript
 torchvision
 TorchVision
 transformative
+triplane
+TriplaneLearnablePositionalEmbedding
+triplanes
 Tripo
 TripoSR
 TTS
 Tsinghua
 TsinghuaNLP
 tunable
 tv
+TwoStreamInterleaveTransformer
 TypeScript
 Udnie
 UHD

notebooks/stable-fast-3d/README.md

@@ -0,0 +1,25 @@
+# Stable Fast 3D Mesh Reconstruction and OpenVINO
+
+<div class="alert alert-block alert-danger"> <b>Important note:</b> This notebook requires python >= 3.9. Please make sure that your environment fulfill to this requirement before running it </div>
+
+[Stable Fast 3D (SF3D)](https://huggingface.co/stabilityai/stable-fast-3d) is a large reconstruction model based on [TripoSR](https://huggingface.co/spaces/stabilityai/TripoSR), which takes in a single image of an object and generates a textured UV-unwrapped 3D mesh asset.
+
+You can find [the source code on GitHub](https://github.com/Stability-AI/stable-fast-3d) and read the paper [SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement](https://arxiv.org/abs/2408.00653).
+
+![Teaser Video](https://github.com/Stability-AI/stable-fast-3d/blob/main/demo_files/teaser.gif?raw=true)
+
+
+## Notebook contents
+The tutorial consists from following steps:
+
+- Prerequisites
+- Get the original model
+- Convert the original model to OpenVINO Intermediate Representation (IR) format
+- Compiling models and prepare pipeline
+- Interactive inference
+
+## Installation instructions
+This is a self-contained example that relies solely on its own code.</br>
+We recommend running the notebook in a virtual environment. You only need a Jupyter server to start.
+For details, please refer to [Installation Guide](../../README.md).
+<img referrerpolicy="no-referrer-when-downgrade" src="https://static.scarf.sh/a.png?x-pxid=5b5a4db0-7875-4bfb-bdbd-01698b5b1a77&file=notebooks/stable-fast-3d/README.md" />