Upload 21 files

.gitattributes

@@ -1,35 +1,34 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,164 @@
+.gradio/
+shap_e_model_cache/
+corgi.png
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

.pre-commit-config.yaml

@@ -0,0 +1,60 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-executables-have-shebangs
+      - id: check-json
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-toml
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+      - id: requirements-txt-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/myint/docformatter
+    rev: v1.7.5
+    hooks:
+      - id: docformatter
+        args: ["--in-place"]
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        args: ["--profile", "black"]
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.9.0
+    hooks:
+      - id: mypy
+        args: ["--ignore-missing-imports"]
+        additional_dependencies:
+          [
+            "types-python-slugify",
+            "types-requests",
+            "types-PyYAML",
+            "types-pytz",
+          ]
+  - repo: https://github.com/psf/black
+    rev: 24.4.0
+    hooks:
+      - id: black
+        language_version: python3.10
+        args: ["--line-length", "119"]
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.7.1
+    hooks:
+      - id: nbstripout
+        args:
+          [
+            "--extra-keys",
+            "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
+          ]
+  - repo: https://github.com/nbQA-dev/nbQA
+    rev: 1.8.5
+    hooks:
+      - id: nbqa-black
+      - id: nbqa-pyupgrade
+        args: ["--py37-plus"]
+      - id: nbqa-isort
+        args: ["--float-to-top"]

.python-version

@@ -0,0 +1 @@
+3.10

.vscode/settings.json

@@ -0,0 +1,30 @@
+{
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": false,
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "source.organizeImports": "explicit"
+        }
+    },
+    "[jupyter]": {
+        "files.insertFinalNewline": false
+    },
+    "black-formatter.args": [
+        "--line-length=119"
+    ],
+    "isort.args": ["--profile", "black"],
+    "flake8.args": [
+        "--max-line-length=119"
+    ],
+    "ruff.lint.args": [
+        "--line-length=119"
+    ],
+    "notebook.output.scrolling": true,
+    "notebook.formatOnCellExecution": true,
+    "notebook.formatOnSave.enabled": true,
+        "notebook.codeActionsOnSave": {
+            "source.organizeImports": "explicit"
+        }
+}

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 hysts
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

LICENSE.Shap-E

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 OpenAI
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,14 +1,17 @@
----
-title: 3D
-emoji: 🖼
-colorFrom: purple
-colorTo: red
-sdk: gradio
-sdk_version: 5.0.1
-app_file: app.py
-pinned: false
-license: apache-2.0
-short_description: 3d_model_generator
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Shap-E
+emoji: 🧢
+colorFrom: yellow
+colorTo: blue
+sdk: gradio
+sdk_version: 5.0.2
+app_file: app.py
+pinned: false
+license: mit
+suggested_hardware: t4-small
+short_description: text-to-3D & image-to-3D
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+https://arxiv.org/abs/2305.02463

app.py

@@ -1,154 +1,33 @@
-import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
-import torch
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    return image, seed
-
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
-
-if __name__ == "__main__":
-    demo.launch()
+#!/usr/bin/env python
+
+import os
+
+import gradio as gr
+import torch
+
+from app_image_to_3d import create_demo as create_demo_image_to_3d
+from app_text_to_3d import create_demo as create_demo_text_to_3d
+from model import Model
+
+DESCRIPTION = "# [Shap-E](https://github.com/openai/shap-e)"
+
+if not torch.cuda.is_available():
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
+
+model = Model()
+
+with gr.Blocks(css_paths="style.css") as demo:
+    gr.Markdown(DESCRIPTION)
+    gr.DuplicateButton(
+        value="Duplicate Space for private use",
+        elem_id="duplicate-button",
+        visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
+    )
+    with gr.Tabs():
+        with gr.Tab(label="Text to 3D"):
+            create_demo_text_to_3d(model)
+        with gr.Tab(label="Image to 3D"):
+            create_demo_image_to_3d(model)
+
+if __name__ == "__main__":
+    demo.queue(max_size=10).launch()

app_image_to_3d.py

@@ -0,0 +1,88 @@
+#!/usr/bin/env python
+
+import pathlib
+import shlex
+import subprocess
+
+import gradio as gr
+import PIL.Image
+import spaces
+
+from model import Model
+from settings import MAX_SEED
+from utils import randomize_seed_fn
+
+
+def create_demo(model: Model) -> gr.Blocks:
+    if not pathlib.Path("corgi.png").exists():
+        subprocess.run(
+            shlex.split(
+                "wget https://raw.githubusercontent.com/openai/shap-e/d99cedaea18e0989e340163dbaeb4b109fa9e8ec/shap_e/examples/example_data/corgi.png -O corgi.png"
+            )
+        )
+    examples = ["corgi.png"]
+
+    @spaces.GPU
+    def process_example_fn(image_path: str) -> str:
+        return model.run_image(image_path)
+
+    @spaces.GPU
+    def run(image: PIL.Image.Image, seed: int, guidance_scale: float, num_inference_steps: int) -> str:
+        return model.run_image(image, seed, guidance_scale, num_inference_steps)
+
+    with gr.Blocks() as demo:
+        with gr.Group():
+            image = gr.Image(label="Input image", show_label=False, type="pil")
+            run_button = gr.Button("Run")
+            result = gr.Model3D(label="Result", show_label=False)
+            with gr.Accordion("Advanced options", open=False):
+                seed = gr.Slider(
+                    label="Seed",
+                    minimum=0,
+                    maximum=MAX_SEED,
+                    step=1,
+                    value=0,
+                )
+                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=1,
+                    maximum=20,
+                    step=0.1,
+                    value=3.0,
+                )
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=2,
+                    maximum=100,
+                    step=1,
+                    value=64,
+                )
+
+        gr.Examples(
+            examples=examples,
+            inputs=image,
+            outputs=result,
+            fn=process_example_fn,
+        )
+
+        run_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+            api_name=False,
+            concurrency_limit=None,
+        ).then(
+            fn=run,
+            inputs=[
+                image,
+                seed,
+                guidance_scale,
+                num_inference_steps,
+            ],
+            outputs=result,
+            api_name="image-to-3d",
+            concurrency_id="gpu",
+            concurrency_limit=1,
+        )
+    return demo

app_text_to_3d.py

@@ -0,0 +1,93 @@
+#!/usr/bin/env python
+
+import gradio as gr
+import spaces
+
+from model import Model
+from settings import MAX_SEED
+from utils import randomize_seed_fn
+
+
+def create_demo(model: Model) -> gr.Blocks:
+    examples = [
+        "A chair that looks like an avocado",
+        "An airplane that looks like a banana",
+        "A spaceship",
+        "A birthday cupcake",
+        "A chair that looks like a tree",
+        "A green boot",
+        "A penguin",
+        "Ube ice cream cone",
+        "A bowl of vegetables",
+    ]
+
+    @spaces.GPU
+    def process_example_fn(prompt: str) -> str:
+        return model.run_text(prompt)
+
+    @spaces.GPU
+    def run(prompt: str, seed: int, guidance_scale: float, num_inference_steps: int) -> str:
+        return model.run_text(prompt, seed, guidance_scale, num_inference_steps)
+
+    with gr.Blocks() as demo:
+        with gr.Group():
+            with gr.Row(elem_id="prompt-container"):
+                prompt = gr.Text(
+                    label="Prompt",
+                    show_label=False,
+                    max_lines=1,
+                    placeholder="Enter your prompt",
+                    submit_btn=True,
+                )
+            result = gr.Model3D(label="Result", show_label=False)
+            with gr.Accordion("Advanced options", open=False):
+                seed = gr.Slider(
+                    label="Seed",
+                    minimum=0,
+                    maximum=MAX_SEED,
+                    step=1,
+                    value=0,
+                )
+                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=1,
+                    maximum=20,
+                    step=0.1,
+                    value=15.0,
+                )
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=2,
+                    maximum=100,
+                    step=1,
+                    value=64,
+                )
+
+        gr.Examples(
+            examples=examples,
+            inputs=prompt,
+            outputs=result,
+            fn=process_example_fn,
+        )
+
+        prompt.submit(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+            api_name=False,
+            concurrency_limit=None,
+        ).then(
+            fn=run,
+            inputs=[
+                prompt,
+                seed,
+                guidance_scale,
+                num_inference_steps,
+            ],
+            outputs=result,
+            api_name="text-to-3d",
+            concurrency_id="gpu",
+            concurrency_limit=1,
+        )
+    return demo

model.py

@@ -0,0 +1,56 @@
+import tempfile
+
+import numpy as np
+import PIL.Image
+import torch
+import trimesh
+from diffusers import ShapEImg2ImgPipeline, ShapEPipeline
+from diffusers.utils import export_to_ply
+
+
+class Model:
+    def __init__(self):
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.pipe = ShapEPipeline.from_pretrained("openai/shap-e", torch_dtype=torch.float16)
+        self.pipe.to(self.device)
+
+        self.pipe_img = ShapEImg2ImgPipeline.from_pretrained("openai/shap-e-img2img", torch_dtype=torch.float16)
+        self.pipe_img.to(self.device)
+
+    def to_glb(self, ply_path: str) -> str:
+        mesh = trimesh.load(ply_path)
+        rot = trimesh.transformations.rotation_matrix(-np.pi / 2, [1, 0, 0])
+        mesh = mesh.apply_transform(rot)
+        rot = trimesh.transformations.rotation_matrix(np.pi, [0, 1, 0])
+        mesh = mesh.apply_transform(rot)
+        mesh_path = tempfile.NamedTemporaryFile(suffix=".glb", delete=False)
+        mesh.export(mesh_path.name, file_type="glb")
+        return mesh_path.name
+
+    def run_text(self, prompt: str, seed: int = 0, guidance_scale: float = 15.0, num_steps: int = 64) -> str:
+        generator = torch.Generator(device=self.device).manual_seed(seed)
+        images = self.pipe(
+            prompt,
+            generator=generator,
+            guidance_scale=guidance_scale,
+            num_inference_steps=num_steps,
+            output_type="mesh",
+        ).images
+        ply_path = tempfile.NamedTemporaryFile(suffix=".ply", delete=False, mode="w+b")
+        export_to_ply(images[0], ply_path.name)
+        return self.to_glb(ply_path.name)
+
+    def run_image(
+        self, image: PIL.Image.Image, seed: int = 0, guidance_scale: float = 3.0, num_steps: int = 64
+    ) -> str:
+        generator = torch.Generator(device=self.device).manual_seed(seed)
+        images = self.pipe_img(
+            image,
+            generator=generator,
+            guidance_scale=guidance_scale,
+            num_inference_steps=num_steps,
+            output_type="mesh",
+        ).images
+        ply_path = tempfile.NamedTemporaryFile(suffix=".ply", delete=False, mode="w+b")
+        export_to_ply(images[0], ply_path.name)
+        return self.to_glb(ply_path.name)

pyproject.toml

@@ -0,0 +1,16 @@
+[project]
+name = "shap-e"
+version = "0.1.0"
+description = ""
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "accelerate>=1.0.0",
+    "diffusers>=0.30.3",
+    "gradio==5.0.2",
+    "spaces>=0.30.3",
+    "torch==2.4.0",
+    "torchvision>=0.19.0",
+    "transformers>=4.45.2",
+    "trimesh>=4.4.9",
+]

requirements.txt

@@ -1,6 +1,258 @@
-accelerate
-diffusers
-invisible_watermark
-torch
-transformers
-xformers
+# This file was autogenerated by uv via the following command:
+#    uv pip compile pyproject.toml -o requirements.txt
+accelerate==1.0.0
+    # via shap-e (pyproject.toml)
+aiofiles==23.2.1
+    # via gradio
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.6.0
+    # via
+    #   gradio
+    #   httpx
+    #   starlette
+certifi==2024.8.30
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.4.0
+    # via requests
+click==8.1.7
+    # via
+    #   typer
+    #   uvicorn
+diffusers==0.30.3
+    # via shap-e (pyproject.toml)
+exceptiongroup==1.2.2
+    # via anyio
+fastapi==0.115.0
+    # via gradio
+ffmpy==0.4.0
+    # via gradio
+filelock==3.16.1
+    # via
+    #   diffusers
+    #   huggingface-hub
+    #   torch
+    #   transformers
+    #   triton
+fsspec==2024.9.0
+    # via
+    #   gradio-client
+    #   huggingface-hub
+    #   torch
+gradio==5.0.2
+    # via
+    #   shap-e (pyproject.toml)
+    #   spaces
+gradio-client==1.4.0
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+httpcore==1.0.6
+    # via httpx
+httpx==0.27.2
+    # via
+    #   gradio
+    #   gradio-client
+    #   spaces
+huggingface-hub==0.25.2
+    # via
+    #   accelerate
+    #   diffusers
+    #   gradio
+    #   gradio-client
+    #   tokenizers
+    #   transformers
+idna==3.10
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+importlib-metadata==8.5.0
+    # via diffusers
+jinja2==3.1.4
+    # via
+    #   gradio
+    #   torch
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.5
+    # via
+    #   gradio
+    #   jinja2
+mdurl==0.1.2
+    # via markdown-it-py
+mpmath==1.3.0
+    # via sympy
+networkx==3.3
+    # via torch
+numpy==1.26.4
+    # via
+    #   accelerate
+    #   diffusers
+    #   gradio
+    #   pandas
+    #   torchvision
+    #   transformers
+    #   trimesh
+nvidia-cublas-cu12==12.1.3.1
+    # via
+    #   nvidia-cudnn-cu12
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cuda-cupti-cu12==12.1.105
+    # via torch
+nvidia-cuda-nvrtc-cu12==12.1.105
+    # via torch
+nvidia-cuda-runtime-cu12==12.1.105
+    # via torch
+nvidia-cudnn-cu12==9.1.0.70
+    # via torch
+nvidia-cufft-cu12==11.0.2.54
+    # via torch
+nvidia-curand-cu12==10.3.2.106
+    # via torch
+nvidia-cusolver-cu12==11.4.5.107
+    # via torch
+nvidia-cusparse-cu12==12.1.0.106
+    # via
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-nccl-cu12==2.20.5
+    # via torch
+nvidia-nvjitlink-cu12==12.6.77
+    # via
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+nvidia-nvtx-cu12==12.1.105
+    # via torch
+orjson==3.10.7
+    # via gradio
+packaging==24.1
+    # via
+    #   accelerate
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   spaces
+    #   transformers
+pandas==2.2.3
+    # via gradio
+pillow==10.4.0
+    # via
+    #   diffusers
+    #   gradio
+    #   torchvision
+psutil==5.9.8
+    # via
+    #   accelerate
+    #   spaces
+pydantic==2.9.2
+    # via
+    #   fastapi
+    #   gradio
+    #   spaces
+pydantic-core==2.23.4
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.18.0
+    # via rich
+python-dateutil==2.9.0.post0
+    # via pandas
+python-multipart==0.0.12
+    # via gradio
+pytz==2024.2
+    # via pandas
+pyyaml==6.0.2
+    # via
+    #   accelerate
+    #   gradio
+    #   huggingface-hub
+    #   transformers
+regex==2024.9.11
+    # via
+    #   diffusers
+    #   transformers
+requests==2.32.3
+    # via
+    #   diffusers
+    #   huggingface-hub
+    #   spaces
+    #   transformers
+rich==13.9.2
+    # via typer
+ruff==0.6.9
+    # via gradio
+safetensors==0.4.5
+    # via
+    #   accelerate
+    #   diffusers
+    #   transformers
+semantic-version==2.10.0
+    # via gradio
+shellingham==1.5.4
+    # via typer
+six==1.16.0
+    # via python-dateutil
+sniffio==1.3.1
+    # via
+    #   anyio
+    #   httpx
+spaces==0.30.3
+    # via shap-e (pyproject.toml)
+starlette==0.38.6
+    # via fastapi
+sympy==1.13.3
+    # via torch
+tokenizers==0.20.0
+    # via transformers
+tomlkit==0.12.0
+    # via gradio
+torch==2.4.0
+    # via
+    #   shap-e (pyproject.toml)
+    #   accelerate
+    #   torchvision
+torchvision==0.19.0
+    # via shap-e (pyproject.toml)
+tqdm==4.66.5
+    # via
+    #   huggingface-hub
+    #   transformers
+transformers==4.45.2
+    # via shap-e (pyproject.toml)
+trimesh==4.4.9
+    # via shap-e (pyproject.toml)
+triton==3.0.0
+    # via torch
+typer==0.12.5
+    # via gradio
+typing-extensions==4.12.2
+    # via
+    #   anyio
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   pydantic
+    #   pydantic-core
+    #   rich
+    #   spaces
+    #   torch
+    #   typer
+    #   uvicorn
+tzdata==2024.2
+    # via pandas
+urllib3==2.2.3
+    # via requests
+uvicorn==0.31.0
+    # via gradio
+websockets==12.0
+    # via gradio-client
+zipp==3.20.2
+    # via importlib-metadata

settings.py

@@ -0,0 +1,3 @@
+import numpy as np
+
+MAX_SEED = np.iinfo(np.int32).max

style.css

@@ -0,0 +1,22 @@
+h1 {
+  text-align: center;
+  display: block;
+}
+
+.contain {
+  max-width: 730px;
+  min-width: 400px;
+  margin: auto;
+  padding-top: 1.5rem;
+}
+
+#prompt-container {
+  gap: 0;
+}
+
+#duplicate-button {
+  margin: auto;
+  color: #fff;
+  background: #1565c0;
+  border-radius: 100vh;
+}

utils.py

@@ -0,0 +1,9 @@
+import random
+
+from settings import MAX_SEED
+
+
+def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+    return seed