Instructions to use HighCWu/Jojo_lora_4bit_training_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use HighCWu/Jojo_lora_4bit_training_v1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev,HighCWu/FLUX.1-Kontext-dev-bnb-hqq-4bit", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("HighCWu/Jojo_lora_4bit_training_v1") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Update train_lora_flux_kontext_16gb_jojo.yaml
Browse files
train_lora_flux_kontext_16gb_jojo.yaml
CHANGED
|
@@ -70,7 +70,7 @@ config:
|
|
| 70 |
dtype: bf16
|
| 71 |
model:
|
| 72 |
# huggingface model name or path.
|
| 73 |
-
name_or_path: "
|
| 74 |
arch: "flux_kontext"
|
| 75 |
quantize: true # We've already used a quantized model
|
| 76 |
quantize_te: true
|
|
|
|
| 70 |
dtype: bf16
|
| 71 |
model:
|
| 72 |
# huggingface model name or path.
|
| 73 |
+
name_or_path: "HighCWu/FLUX.1-Kontext-dev-bnb-hqq-4bit"
|
| 74 |
arch: "flux_kontext"
|
| 75 |
quantize: true # We've already used a quantized model
|
| 76 |
quantize_te: true
|