Instructions to use lodestones/Chroma1-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lodestones/Chroma1-Base with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lodestones/Chroma1-Base", 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
Enable timestep shifting
#4
by dxqb - opened
scheduler/scheduler_config.json
CHANGED
|
@@ -1,6 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
-
"_diffusers_version": "0.
|
|
|
|
| 4 |
"num_train_timesteps": 1000,
|
| 5 |
-
"
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
+
"_diffusers_version": "0.35.1",
|
| 4 |
+
"invert_sigmas": false,
|
| 5 |
"num_train_timesteps": 1000,
|
| 6 |
+
"shift": 3.0,
|
| 7 |
+
"shift_terminal": null,
|
| 8 |
+
"stochastic_sampling": false,
|
| 9 |
+
"time_shift_type": "exponential",
|
| 10 |
+
"use_beta_sigmas": false,
|
| 11 |
+
"use_dynamic_shifting": false,
|
| 12 |
+
"use_exponential_sigmas": false,
|
| 13 |
+
"use_karras_sigmas": false
|
| 14 |
+
}
|