Image-to-Image
Diffusers
Safetensors
FluxKontextPipeline
flux
flux.1
kontext
flux dev
lightning
turbo
Instructions to use buildborderless/FLUX.MF-Kontext_Lightning-8s-4bit_nf4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use buildborderless/FLUX.MF-Kontext_Lightning-8s-4bit_nf4 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("buildborderless/FLUX.MF-Kontext_Lightning-8s-4bit_nf4", 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
| { | |
| "_class_name": "FluxTransformer2DModel", | |
| "_diffusers_version": "0.34.0.dev0", | |
| "_name_or_path": "/home/user/.cache/huggingface/hub/models--black-forest-labs--FLUX.1-Kontext-dev/snapshots/af58063aa431f4d2bbc11ae46f57451d4416a170/transformer", | |
| "attention_head_dim": 128, | |
| "axes_dims_rope": [ | |
| 16, | |
| 56, | |
| 56 | |
| ], | |
| "guidance_embeds": true, | |
| "in_channels": 64, | |
| "joint_attention_dim": 4096, | |
| "num_attention_heads": 24, | |
| "num_layers": 19, | |
| "num_single_layers": 38, | |
| "out_channels": null, | |
| "patch_size": 1, | |
| "pooled_projection_dim": 768 | |
| } | |