Instructions to use jasperai/flash-sd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jasperai/flash-sd with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("jasperai/flash-sd") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -55,7 +55,7 @@ The model was trained for 20k iterations on 2 H100 GPUs (representing approx. **
|
|
| 55 |
|
| 56 |
**Metrics on COCO 2017 validation set**
|
| 57 |
- FID-5k: 22.6 (2 NFE) / 22.5 (4 NFE)
|
| 58 |
-
- CLIP Score (ViT-g/14): 0.306 (2 NFE) /
|
| 59 |
|
| 60 |
**Metrics on COCO 2014 validation**
|
| 61 |
- FID-30k:
|
|
|
|
| 55 |
|
| 56 |
**Metrics on COCO 2017 validation set**
|
| 57 |
- FID-5k: 22.6 (2 NFE) / 22.5 (4 NFE)
|
| 58 |
+
- CLIP Score (ViT-g/14): 0.306 (2 NFE) / 0.311 (4 NFE)
|
| 59 |
|
| 60 |
**Metrics on COCO 2014 validation**
|
| 61 |
- FID-30k:
|