Image-to-Image
Diffusers
Safetensors
Diffusion Single File
English
FluxKontextPipeline
image-generation
flux
Instructions to use AlekseyCalvin/Flux_Kontext_Dev_fp8_scaled_diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AlekseyCalvin/Flux_Kontext_Dev_fp8_scaled_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("AlekseyCalvin/Flux_Kontext_Dev_fp8_scaled_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] - Diffusion Single File
How to use AlekseyCalvin/Flux_Kontext_Dev_fp8_scaled_diffusers with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Update vae/config.json
Browse files- vae/config.json +3 -3
vae/config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "AutoencoderKL",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
-
"_name_or_path": "
|
| 5 |
"act_fn": "silu",
|
| 6 |
"block_out_channels": [
|
| 7 |
128,
|
|
@@ -35,4 +35,4 @@
|
|
| 35 |
],
|
| 36 |
"use_post_quant_conv": false,
|
| 37 |
"use_quant_conv": false
|
| 38 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.35.0.dev0",
|
| 4 |
+
"_name_or_path": "./FLUX.1-Kontext-dev/vae",
|
| 5 |
"act_fn": "silu",
|
| 6 |
"block_out_channels": [
|
| 7 |
128,
|
|
|
|
| 35 |
],
|
| 36 |
"use_post_quant_conv": false,
|
| 37 |
"use_quant_conv": false
|
| 38 |
+
}
|