Text-to-Image
Diffusers
TensorBoard
stable-diffusion
diffusion
distillation
flow-matching
geometric-deep-learning
research
Instructions to use AbstractPhil/sd15-flow-matching with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AbstractPhil/sd15-flow-matching with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AbstractPhil/sd15-flow-matching", 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 Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,8 @@ I will remove the faulty checkpoints and the correct checkpoints, which are earl
|
|
| 18 |
|
| 19 |
It's basically just blobs as expected, so don't expect much yet. It has a long way to go.
|
| 20 |
|
|
|
|
|
|
|
| 21 |
# More faults more problems still managed to salvage the real one
|
| 22 |
How absurd and difficult anything SD15 has been to debug.
|
| 23 |
|
|
|
|
| 18 |
|
| 19 |
It's basically just blobs as expected, so don't expect much yet. It has a long way to go.
|
| 20 |
|
| 21 |
+
The current one is showing response to shift as it should. This will require an additional 40 or so epochs most likely before convergence is possible and I will be uploading every epoch as pt from this point forward to guarantee cohesion and transparency.
|
| 22 |
+
|
| 23 |
# More faults more problems still managed to salvage the real one
|
| 24 |
How absurd and difficult anything SD15 has been to debug.
|
| 25 |
|