Instructions to use tommycik/ControlNetHedNew with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tommycik/ControlNetHedNew with Diffusers:
pip install -U diffusers transformers accelerate
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline controlnet = ControlNetModel.from_pretrained("tommycik/ControlNetHedNew") pipe = StableDiffusionControlNetPipeline.from_pretrained( "black-forest-labs/FLUX.1-dev", controlnet=controlnet ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Upload training_config.yaml with huggingface_hub
Browse files- training_config.yaml +13 -0
training_config.yaml
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
N4: false
|
| 2 |
+
checkpointing_steps: 250
|
| 3 |
+
controlnet_model: Xlabs-AI/flux-controlnet-hed-diffusers
|
| 4 |
+
controlnet_type: hed
|
| 5 |
+
gradient_accumulation_steps: 4
|
| 6 |
+
hub_model_id: tommycik/ControlNetHedNew
|
| 7 |
+
learning_rate: 5e-06
|
| 8 |
+
mixed_precision: bf16
|
| 9 |
+
resolution: 512
|
| 10 |
+
steps: 1000
|
| 11 |
+
train_batch_size: 2
|
| 12 |
+
validation_image: None
|
| 13 |
+
validation_steps: 125
|