Instructions to use BiliSakura/ADM-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/ADM-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BiliSakura/ADM-diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Upload folder using huggingface_hub
Browse files- ADM-G-256/README.md +1 -0
- ADM-G-256/__pycache__/pipeline.cpython-312.pyc +0 -0
- ADM-G-256/classifier/__pycache__/classifier_adm.cpython-312.pyc +0 -0
- ADM-G-256/classifier/__pycache__/modeling_adm.cpython-312.pyc +0 -0
- ADM-G-256/pipeline.py +1 -0
- ADM-G-256/scheduler/__pycache__/scheduling_adm.cpython-312.pyc +0 -0
- ADM-G-512/README.md +1 -0
- ADM-G-512/__pycache__/pipeline.cpython-312.pyc +0 -0
- ADM-G-512/classifier/__pycache__/classifier_adm.cpython-312.pyc +0 -0
- ADM-G-512/pipeline.py +1 -0
- README.md +1 -0
ADM-G-256/README.md
CHANGED
|
@@ -29,6 +29,7 @@ pipe = DiffusionPipeline.from_pretrained(
|
|
| 29 |
str(model_dir),
|
| 30 |
local_files_only=True,
|
| 31 |
custom_pipeline=str(model_dir / "pipeline.py"),
|
|
|
|
| 32 |
torch_dtype=torch.bfloat16,
|
| 33 |
)
|
| 34 |
pipe = pipe.to("cuda")
|
|
|
|
| 29 |
str(model_dir),
|
| 30 |
local_files_only=True,
|
| 31 |
custom_pipeline=str(model_dir / "pipeline.py"),
|
| 32 |
+
trust_remote_code=True,
|
| 33 |
torch_dtype=torch.bfloat16,
|
| 34 |
)
|
| 35 |
pipe = pipe.to("cuda")
|
ADM-G-256/__pycache__/pipeline.cpython-312.pyc
ADDED
|
Binary file (14.1 kB). View file
|
|
|
ADM-G-256/classifier/__pycache__/classifier_adm.cpython-312.pyc
ADDED
|
Binary file (32.3 kB). View file
|
|
|
ADM-G-256/classifier/__pycache__/modeling_adm.cpython-312.pyc
ADDED
|
Binary file (41.2 kB). View file
|
|
|
ADM-G-256/pipeline.py
CHANGED
|
@@ -35,6 +35,7 @@ EXAMPLE_DOC_STRING = """
|
|
| 35 |
... str(model_dir),
|
| 36 |
... local_files_only=True,
|
| 37 |
... custom_pipeline=str(model_dir / "pipeline.py"),
|
|
|
|
| 38 |
... torch_dtype=torch.bfloat16,
|
| 39 |
... )
|
| 40 |
>>> pipe = pipe.to("cuda")
|
|
|
|
| 35 |
... str(model_dir),
|
| 36 |
... local_files_only=True,
|
| 37 |
... custom_pipeline=str(model_dir / "pipeline.py"),
|
| 38 |
+
... trust_remote_code=True,
|
| 39 |
... torch_dtype=torch.bfloat16,
|
| 40 |
... )
|
| 41 |
>>> pipe = pipe.to("cuda")
|
ADM-G-256/scheduler/__pycache__/scheduling_adm.cpython-312.pyc
ADDED
|
Binary file (33.7 kB). View file
|
|
|
ADM-G-512/README.md
CHANGED
|
@@ -36,6 +36,7 @@ pipe = DiffusionPipeline.from_pretrained(
|
|
| 36 |
str(model_dir),
|
| 37 |
local_files_only=True,
|
| 38 |
custom_pipeline=str(model_dir / "pipeline.py"),
|
|
|
|
| 39 |
torch_dtype=torch.bfloat16,
|
| 40 |
)
|
| 41 |
pipe = pipe.to("cuda")
|
|
|
|
| 36 |
str(model_dir),
|
| 37 |
local_files_only=True,
|
| 38 |
custom_pipeline=str(model_dir / "pipeline.py"),
|
| 39 |
+
trust_remote_code=True,
|
| 40 |
torch_dtype=torch.bfloat16,
|
| 41 |
)
|
| 42 |
pipe = pipe.to("cuda")
|
ADM-G-512/__pycache__/pipeline.cpython-312.pyc
ADDED
|
Binary file (14.1 kB). View file
|
|
|
ADM-G-512/classifier/__pycache__/classifier_adm.cpython-312.pyc
ADDED
|
Binary file (32.3 kB). View file
|
|
|
ADM-G-512/pipeline.py
CHANGED
|
@@ -35,6 +35,7 @@ EXAMPLE_DOC_STRING = """
|
|
| 35 |
... str(model_dir),
|
| 36 |
... local_files_only=True,
|
| 37 |
... custom_pipeline=str(model_dir / "pipeline.py"),
|
|
|
|
| 38 |
... torch_dtype=torch.bfloat16,
|
| 39 |
... )
|
| 40 |
>>> pipe = pipe.to("cuda")
|
|
|
|
| 35 |
... str(model_dir),
|
| 36 |
... local_files_only=True,
|
| 37 |
... custom_pipeline=str(model_dir / "pipeline.py"),
|
| 38 |
+
... trust_remote_code=True,
|
| 39 |
... torch_dtype=torch.bfloat16,
|
| 40 |
... )
|
| 41 |
>>> pipe = pipe.to("cuda")
|
README.md
CHANGED
|
@@ -62,6 +62,7 @@ pipe = DiffusionPipeline.from_pretrained(
|
|
| 62 |
str(model_dir),
|
| 63 |
local_files_only=True,
|
| 64 |
custom_pipeline=str(model_dir / "pipeline.py"),
|
|
|
|
| 65 |
torch_dtype=torch.bfloat16,
|
| 66 |
)
|
| 67 |
pipe = pipe.to("cuda")
|
|
|
|
| 62 |
str(model_dir),
|
| 63 |
local_files_only=True,
|
| 64 |
custom_pipeline=str(model_dir / "pipeline.py"),
|
| 65 |
+
trust_remote_code=True,
|
| 66 |
torch_dtype=torch.bfloat16,
|
| 67 |
)
|
| 68 |
pipe = pipe.to("cuda")
|