Instructions to use szxllm/MSD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use szxllm/MSD with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("szxllm/MSD", torch_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
Update eval.py
Browse files
eval.py
CHANGED
|
@@ -427,7 +427,7 @@ def main():
|
|
| 427 |
mode="clean",
|
| 428 |
num_workers=min(os.cpu_count(), 8) # Use reasonable number of workers
|
| 429 |
)
|
| 430 |
-
fid_score=fid_score
|
| 431 |
print(f"FID Score: {fid_score:.2f}")
|
| 432 |
except Exception as e:
|
| 433 |
print(f"Error calculating FID: {e}")
|
|
@@ -479,7 +479,7 @@ def main():
|
|
| 479 |
|
| 480 |
|
| 481 |
final_clip_score = clip_scorer.compute().item()
|
| 482 |
-
clip_t_score = final_clip_score/100
|
| 483 |
print(f"CLIP-T Score : {clip_t_score:.3f}")
|
| 484 |
|
| 485 |
except Exception as e:
|
|
|
|
| 427 |
mode="clean",
|
| 428 |
num_workers=min(os.cpu_count(), 8) # Use reasonable number of workers
|
| 429 |
)
|
| 430 |
+
fid_score=fid_score
|
| 431 |
print(f"FID Score: {fid_score:.2f}")
|
| 432 |
except Exception as e:
|
| 433 |
print(f"Error calculating FID: {e}")
|
|
|
|
| 479 |
|
| 480 |
|
| 481 |
final_clip_score = clip_scorer.compute().item()
|
| 482 |
+
clip_t_score = final_clip_score/100
|
| 483 |
print(f"CLIP-T Score : {clip_t_score:.3f}")
|
| 484 |
|
| 485 |
except Exception as e:
|