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", 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] hf download SceneWorks/flux2-dev-mlx --local-dir flux2-dev-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Draw Things
- DiffusionBee
- Atomic Chat
Commit History
-
Add missing scheduler/scheduler_config.json to q4/q8/bf16 tiers (fixes false-incomplete gate, GH SceneWorks/SceneWorks#1858)
Verified signature2868b14
-
Upload folder using huggingface_hub
Verified signature0c9b86f -
Upload folder using huggingface_hub
Verified signatureef8e0d3 -
Upload folder using huggingface_hub
Verified signature6bd8d3d -
Upload folder using huggingface_hub
Verified signature2686696 -
Upload bf16/model_index.json with huggingface_hub
Verified signatured83e845 -
Upload bf16/LICENSE.md with huggingface_hub
Verified signature1fc23ae