Text-to-Image
Diffusers
hidream
hidream-diffusers
image-to-image
simpletuner
Not-For-All-Audiences
lora
controlnet
template:sd-lora
standard
Instructions to use ControlNetLoRA/hidream-i1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ControlNetLoRA/hidream-i1 with Diffusers:
pip install -U diffusers transformers accelerate
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline controlnet = ControlNetModel.from_pretrained("ControlNetLoRA/hidream-i1") pipe = StableDiffusionControlNetPipeline.from_pretrained( "HiDream-ai/HiDream-I1-Full", controlnet=controlnet ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Model card auto-generated by SimpleTuner
Browse files
README.md
CHANGED
|
@@ -55,8 +55,8 @@ You may reuse the base model text encoder for inference.
|
|
| 55 |
|
| 56 |
## Training settings
|
| 57 |
|
| 58 |
-
- Training epochs:
|
| 59 |
-
- Training steps:
|
| 60 |
- Learning rate: 0.0001
|
| 61 |
- Learning rate schedule: constant
|
| 62 |
- Warmup steps: 500
|
|
@@ -73,8 +73,8 @@ You may reuse the base model text encoder for inference.
|
|
| 73 |
- Caption dropout probability: 0.0%
|
| 74 |
|
| 75 |
|
| 76 |
-
- LoRA Rank:
|
| 77 |
-
- LoRA Alpha:
|
| 78 |
- LoRA Dropout: 0.1
|
| 79 |
- LoRA initialisation style: default
|
| 80 |
|
|
|
|
| 55 |
|
| 56 |
## Training settings
|
| 57 |
|
| 58 |
+
- Training epochs: 0
|
| 59 |
+
- Training steps: 2
|
| 60 |
- Learning rate: 0.0001
|
| 61 |
- Learning rate schedule: constant
|
| 62 |
- Warmup steps: 500
|
|
|
|
| 73 |
- Caption dropout probability: 0.0%
|
| 74 |
|
| 75 |
|
| 76 |
+
- LoRA Rank: 1
|
| 77 |
+
- LoRA Alpha: 1.0
|
| 78 |
- LoRA Dropout: 0.1
|
| 79 |
- LoRA initialisation style: default
|
| 80 |
|