Instructions to use hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers 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("hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers", dtype=torch.bfloat16, device_map="cuda") 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
Upload AdaptiveProjectedMixGuidance
Browse files
guider/guider_config.json
CHANGED
|
@@ -1,10 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"_class_name": "
|
| 3 |
"_diffusers_version": "0.36.0.dev0",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"enabled": false,
|
|
|
|
| 5 |
"guidance_rescale": 0.0,
|
| 6 |
"guidance_scale": 3.5,
|
| 7 |
-
"distilled_guidance_scale": 3.25,
|
| 8 |
"start": 0.0,
|
| 9 |
"stop": 1.0,
|
| 10 |
"use_original_formulation": false
|
|
|
|
| 1 |
{
|
| 2 |
+
"_class_name": "AdaptiveProjectedMixGuidance",
|
| 3 |
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
+
"adaptive_projected_guidance_momentum": -0.5,
|
| 5 |
+
"adaptive_projected_guidance_rescale": 10.0,
|
| 6 |
+
"adaptive_projected_guidance_scale": 10.0,
|
| 7 |
+
"adaptive_projected_guidance_start_step": 5,
|
| 8 |
+
"distilled_guidance_scale": 3.25,
|
| 9 |
"enabled": false,
|
| 10 |
+
"eta": 0.0,
|
| 11 |
"guidance_rescale": 0.0,
|
| 12 |
"guidance_scale": 3.5,
|
|
|
|
| 13 |
"start": 0.0,
|
| 14 |
"stop": 1.0,
|
| 15 |
"use_original_formulation": false
|