Text-to-Image
Diffusers
Safetensors
MageFlowPipeline
image-generation
image-editing
diffusion
rectified-flow
mage-flow
Instructions to use SceneWorks/Mage-Flow-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SceneWorks/Mage-Flow-Base 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/Mage-Flow-Base", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
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.d642341 -
feat(sc-14980): physical per-tier MLX DiT artifacts (bf16/q8/q4)
Verified signature2c0b473 -
chore: sc-14980 remove throughput probe
Verified signature62b44b6 -
chore: sc-14980 throughput probe
Verified signature5a564e3 -
chore: sc-14980 remove write-access probe
Verified signaturec701c00 -
chore: sc-14980 write-access probe
Verified signaturee4a7a14
-
Add files using upload-large-folder tool
Verified signaturea160c0a -
initial commit
Verified signatureb9d686d