Unconditional Image Generation
Diffusers
Safetensors
English
fit
image-generation
class-conditional
imagenet
Instructions to use BiliSakura/FiT-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/FiT-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/FiT-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
Fix generator determinism: forward generator through scheduler steps and seeded noise
Browse files- FiTv1-XL-2-256/pipeline.py +2 -0
- FiTv2-3B-2-512/pipeline.py +1 -1
FiTv1-XL-2-256/pipeline.py
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
Load with native Hugging Face diffusers and trust_remote_code=True.
|
| 3 |
"""
|
| 4 |
|
|
|
|
|
|
|
| 5 |
import importlib
|
| 6 |
import inspect
|
| 7 |
import json
|
|
|
|
| 2 |
Load with native Hugging Face diffusers and trust_remote_code=True.
|
| 3 |
"""
|
| 4 |
|
| 5 |
+
from __future__ import annotations
|
| 6 |
+
|
| 7 |
import importlib
|
| 8 |
import inspect
|
| 9 |
import json
|
FiTv2-3B-2-512/pipeline.py
CHANGED
|
@@ -21,7 +21,7 @@ from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineO
|
|
| 21 |
from diffusers.schedulers import KarrasDiffusionSchedulers
|
| 22 |
from diffusers.utils.torch_utils import randn_tensor
|
| 23 |
|
| 24 |
-
DEFAULT_NATIVE_RESOLUTION =
|
| 25 |
|
| 26 |
EXAMPLE_DOC_STRING = """
|
| 27 |
Examples:
|
|
|
|
| 21 |
from diffusers.schedulers import KarrasDiffusionSchedulers
|
| 22 |
from diffusers.utils.torch_utils import randn_tensor
|
| 23 |
|
| 24 |
+
DEFAULT_NATIVE_RESOLUTION = 256
|
| 25 |
|
| 26 |
EXAMPLE_DOC_STRING = """
|
| 27 |
Examples:
|