Instructions to use alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Alpha with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Alpha", 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -27,7 +27,7 @@ This repository provides a Inpainting ControlNet checkpoint for [FLUX.1-dev](htt
|
|
| 27 |
ComfyUI Usage Tips:
|
| 28 |
|
| 29 |
* Using the `t5xxl-FP16` and `flux1-dev-fp8` models for 28-step inference, the GPU memory usage is 27GB. The inference time with `cfg=3.5` is 27 seconds, while without `cfg=1` it is 15 seconds. `Hyper-FLUX-lora` can be used to accelerate inference.
|
| 30 |
-
* You can try adjusting the parameters `control-strength`, `control-end-percent`, and `cfg` to achieve better results.
|
| 31 |
* The following example uses `control-strength` = 0.9 & `control-end-percent` = 1.0 & `cfg` = 3.5
|
| 32 |
|
| 33 |
| Input | Output | Prompt |
|
|
|
|
| 27 |
ComfyUI Usage Tips:
|
| 28 |
|
| 29 |
* Using the `t5xxl-FP16` and `flux1-dev-fp8` models for 28-step inference, the GPU memory usage is 27GB. The inference time with `cfg=3.5` is 27 seconds, while without `cfg=1` it is 15 seconds. `Hyper-FLUX-lora` can be used to accelerate inference.
|
| 30 |
+
* You can try adjusting(lower) the parameters `control-strength`, `control-end-percent`, and `cfg` to achieve better results.
|
| 31 |
* The following example uses `control-strength` = 0.9 & `control-end-percent` = 1.0 & `cfg` = 3.5
|
| 32 |
|
| 33 |
| Input | Output | Prompt |
|