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
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,11 @@ tags:
|
|
| 13 |
library_name: diffusers
|
| 14 |
pipeline_tag: text-to-image
|
| 15 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
# The plan for restoration
|
| 18 |
The timestep bias hurt the model yes, but it still inferences using the flow-pattern matching when utilizing the teacher's timesteps and DDIM.
|
|
|
|
| 13 |
library_name: diffusers
|
| 14 |
pipeline_tag: text-to-image
|
| 15 |
---
|
| 16 |
+
# flow lune is ready for toying with
|
| 17 |
+
https://huggingface.co/AbstractPhil/sd15-flow-lune
|
| 18 |
+
|
| 19 |
+
The pretraining was fairly successfull and the instruction for use are tied to the repo. The model will function as proof of concept.
|
| 20 |
+
|
| 21 |
|
| 22 |
# The plan for restoration
|
| 23 |
The timestep bias hurt the model yes, but it still inferences using the flow-pattern matching when utilizing the teacher's timesteps and DDIM.
|