Instructions to use SceneWorks/flux2-dev-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SceneWorks/flux2-dev-mlx with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SceneWorks/flux2-dev-mlx", torch_dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - MLX
How to use SceneWorks/flux2-dev-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir flux2-dev-mlx SceneWorks/flux2-dev-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Draw Things
- DiffusionBee
Add missing scheduler/scheduler_config.json to q4/q8/bf16 tiers (fixes false-incomplete gate, GH SceneWorks/SceneWorks#1858)
2868b14 verified | { | |
| "_class_name": "FlowMatchEulerDiscreteScheduler", | |
| "_diffusers_version": "0.36.0.dev0", | |
| "base_image_seq_len": 256, | |
| "base_shift": 0.5, | |
| "invert_sigmas": false, | |
| "max_image_seq_len": 4096, | |
| "max_shift": 1.15, | |
| "num_train_timesteps": 1000, | |
| "shift": 3.0, | |
| "shift_terminal": null, | |
| "stochastic_sampling": false, | |
| "time_shift_type": "exponential", | |
| "use_beta_sigmas": false, | |
| "use_dynamic_shifting": true, | |
| "use_exponential_sigmas": false, | |
| "use_karras_sigmas": false | |
| } | |