init

.gitattributes

@@ -0,0 +1,35 @@
+*.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

.gitignore

@@ -0,0 +1,164 @@
+.gradio
+
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/

README.md

@@ -0,0 +1,13 @@
+---
+title: Refiners SD1.5
+emoji: 🕯️
+colorFrom: green
+colorTo: pink
+sdk: gradio
+sdk_version: 5.1.0
+app_file: src/app.py
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

pyproject.toml

@@ -0,0 +1,2 @@
+[tool.ruff]
+line-length = 120

requirements.txt

@@ -0,0 +1,2 @@
+git+https://github.com/finegrain-ai/refiners@06204731093d8055e65b21b4da2ce586737d6ea4
+pillow-heif>=0.18.0

src/app.py

@@ -0,0 +1,190 @@
+import gradio as gr  # pyright: ignore[reportMissingTypeStubs]
+import pillow_heif  # pyright: ignore[reportMissingTypeStubs]
+import spaces  # pyright: ignore[reportMissingTypeStubs]
+import torch
+from huggingface_hub import (  # pyright: ignore[reportMissingTypeStubs]
+    hf_hub_download,  # pyright: ignore[reportUnknownVariableType]
+)
+from PIL import Image
+from refiners.fluxion.utils import manual_seed, no_grad
+from refiners.foundationals.latent_diffusion.stable_diffusion_1 import StableDiffusion_1
+
+pillow_heif.register_heif_opener()  # pyright: ignore[reportUnknownMemberType]
+pillow_heif.register_avif_opener()  # pyright: ignore[reportUnknownMemberType]
+
+TITLE = """
+# SD1.5 with Refiners
+"""
+
+# initialize the model, on the cpu
+DEVICE_CPU = torch.device("cpu")
+DEVICE_GPU = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+DTYPE = torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float32
+
+model = StableDiffusion_1(device=DEVICE_CPU, dtype=DTYPE)
+model.unet.load_from_safetensors(
+    tensors_path=hf_hub_download(
+        repo_id="refiners/sd15.unet",
+        filename="model.safetensors",
+        revision="6b01fc610c7465fa79e44c52c4d2eb0ea56821c9",
+    )
+)
+model.lda.load_from_safetensors(
+    tensors_path=hf_hub_download(
+        repo_id="refiners/sd15.autoencoder",
+        filename="model.safetensors",
+        revision="7565efe4812d8e14072111ab326b15eea4c908a5",
+    )
+)
+model.clip_text_encoder.load_from_safetensors(
+    tensors_path=hf_hub_download(
+        repo_id="refiners/sd15.text_encoder",
+        filename="model.safetensors",
+        revision="1b5023ecf0d646b7403f4ad182b6f0ab6b251fef",
+    )
+)
+
+# "move" the model to the gpu, this is handled/intercepted by Zero GPU
+model.to(device=DEVICE_GPU, dtype=DTYPE)
+model.unet.to(device=DEVICE_GPU, dtype=DTYPE)
+model.lda.to(device=DEVICE_GPU, dtype=DTYPE)
+model.clip_text_encoder.to(device=DEVICE_GPU, dtype=DTYPE)
+model.solver.to(device=DEVICE_GPU, dtype=DTYPE)
+model.device = DEVICE_GPU
+model.dtype = DTYPE
+
+
+@spaces.GPU
+@no_grad()
+def process(
+    prompt: str,
+    negative_prompt: str,
+    condition_scale: float,
+    num_inference_steps: int,
+    seed: int,
+) -> Image.Image:
+    assert condition_scale >= 0
+    assert num_inference_steps > 0
+    assert seed >= 0
+
+    # set the seed
+    manual_seed(seed)
+
+    # compute embeddings
+    clip_text_embedding = model.compute_clip_text_embedding(
+        text=prompt,
+        negative_text=negative_prompt,
+    )
+
+    # init latents
+    x = model.init_latents(size=(512, 512))
+
+    # denoise latents
+    for step in model.steps:
+        x = model(
+            x,
+            step=step,
+            clip_text_embedding=clip_text_embedding,
+            condition_scale=condition_scale,
+        )
+
+    # decode denoised latents
+    image = model.lda.latents_to_image(x)
+
+    return image
+
+
+with gr.Blocks() as demo:
+    gr.Markdown(TITLE)
+
+    with gr.Column():
+        with gr.Row():
+            prompt = gr.Text(
+                label="Prompt",
+                show_label=False,
+                max_lines=1,
+                placeholder="Enter your prompt",
+                container=False,
+            )
+            run_button = gr.Button(
+                value="Run",
+                scale=0,
+            )
+
+        output_image = gr.Image(
+            label="Output Image",
+            image_mode="RGB",
+            type="pil",
+        )
+
+    with gr.Accordion("Advanced Settings", open=True):
+        negative_prompt = gr.Textbox(
+            label="Negative Prompt",
+            placeholder="Enter your (optional) negative prompt",
+        )
+        seed = gr.Slider(
+            label="Seed",
+            minimum=0,
+            maximum=100_000,
+            value=2,
+            step=1,
+        )
+        condition_scale = gr.Slider(
+            label="Condition scale",
+            minimum=0,
+            maximum=20,
+            value=7.5,
+            step=0.05,
+        )
+        num_inference_steps = gr.Slider(
+            label="Number of inference steps",
+            minimum=1,
+            maximum=50,
+            value=30,
+            step=1,
+        )
+
+    run_button.click(
+        fn=process,
+        inputs=[
+            prompt,
+            negative_prompt,
+            condition_scale,
+            num_inference_steps,
+            seed,
+        ],
+        outputs=output_image,
+    )
+
+    gr.Examples(  # pyright: ignore[reportUnknownMemberType]
+        examples=[
+            [
+                "a cute cat, detailed high-quality professional image",
+                "lowres, bad anatomy, bad hands, cropped, worst quality",
+                7.5,
+                30,
+                2,
+            ],
+            [
+                "a cute dog, detailed high-quality professional image",
+                "lowres, bad anatomy, bad hands, cropped, worst quality",
+                7.5,
+                30,
+                2,
+            ],
+        ],
+        inputs=[
+            prompt,
+            negative_prompt,
+            condition_scale,
+            num_inference_steps,
+            seed,
+        ],
+        outputs=output_image,
+        fn=process,
+        cache_examples=True,
+        cache_mode="lazy",
+        run_on_click=False,
+    )
+
+demo.launch()