Image-to-Image
Diffusers
Safetensors
MageFlowPipeline
image-editing
instruction-based-editing
diffusion
rectified-flow
mage-flow
Instructions to use SceneWorks/Mage-Flow-Edit-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SceneWorks/Mage-Flow-Edit-Base 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("SceneWorks/Mage-Flow-Edit-Base", 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
Commit History
-
sc-15071: regenerate the q4 tier with the 8-bit precision floors
Verified signatureThe previous q4 artifact was packed uniformly at 4 bits, which made the tier render a repeating tiled texture instead of the prompt. norm_out.linear (the output head's adaLN modulation) and the Qwen3-VL LM decoder layers are now packed at 8 bits; everything else is unchanged. q8 and bf16 are untouched.6c119cd -
feat(sc-14980): physical per-tier MLX DiT artifacts (bf16/q8/q4)
Verified signature199b4ca
-
Add files using upload-large-folder tool
Verified signature5345fa8 -
initial commit
Verified signature9ce5109