Text-to-Image
Diffusers
Safetensors
flow-matching
pyramidal-unet
256x256
ettin-150m
from-scratch
ra
udit
Instructions to use AiArtLab/Ra with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AiArtLab/Ra with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AiArtLab/Ra", 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
Card: butterflies first (validated), then FLUX-Reason
Browse files
README.md
CHANGED
|
@@ -25,14 +25,16 @@ restarted at 1e-4 on step 192 000, so it is mid-recovery and will be replaced).
|
|
| 25 |
|
| 26 |
## Examples
|
| 27 |
|
| 28 |
-
|
| 29 |
-
|
| 30 |
|
| 31 |
-
<img src="docs/img/
|
| 32 |
|
| 33 |
-
|
|
|
|
|
|
|
| 34 |
|
| 35 |
-
<img src="docs/img/
|
| 36 |
|
| 37 |
## Usage
|
| 38 |
|
|
|
|
| 25 |
|
| 26 |
## Examples
|
| 27 |
|
| 28 |
+
Validated on the butterfly set first — step 20 003, the stage that proved the architecture
|
| 29 |
+
(63% of the AE's own high-frequency ceiling at 256²):
|
| 30 |
|
| 31 |
+
<img src="docs/img/samples_butterflies_20k.png" width="100%"/>
|
| 32 |
|
| 33 |
+
Now training on FLUX-Reason-6M — bundled snapshot, step 212 000, 256 px, 16 body steps, 8 head steps,
|
| 34 |
+
cfg 2.5, seed 0 (fox · sailboat · fisherman · sunflowers · blue morpho · white butterfly ·
|
| 35 |
+
swallowtail · monarch):
|
| 36 |
|
| 37 |
+
<img src="docs/img/samples.png" width="100%"/>
|
| 38 |
|
| 39 |
## Usage
|
| 40 |
|