MLX-Gen Documentation¶
MLX-Gen is an MLX-native generative image and video runtime forked from mflux. It can be used directly from the command line or embedded in Python applications that need local Apple Silicon generation.
Guides¶
- Getting started: install MLX-Gen, inspect the CLI, prepare or download model files, run image generation/editing, restore or upscale with SeedVR2, and start Wan or Bernini video workflows.
- Architecture: system overview and model-file lifecycle diagrams, package and factored-source shapes, role-aware routing, command boundaries, runtime failure contract, and Python integration boundary.
- API and CLI: public
mlxgencommand surface, generation router behavior, image/video/reference input roles, image editing, SeedVR2, Wan video controls, Bernini R2V/RV2V/V2V, metadata, and capability schema 8. - Image edit modes: plain-language guide to latent img2img, edit-reference, masked edit/inpaint, base-Qwen control-inpaint, Qwen structured control, multi-reference, generative reframe, and outpaint, including what each mode is good at and what to expect from the output.
- Masked editing: the canonical masked-edit page — request contract, per-model route matrix with proof grades, per-family behavior (Qwen edit and base routes with the tunable
--mask-strengthwarm start, Z-Image Turbo, FLUX.2 Klein, video masks), and route selection advice. - Qwen route matrix: current MLX-Gen route truth for Qwen Image and Qwen Image Edit, mapping public
mlxgencapability ids to the upstream Diffusers Qwen pipelines and the exact proof surfaces that already exist. - Qwen localized editing: plain-language explanation of Qwen masked edit, Qwen structured control, and shipped base-Qwen control-inpaint, including definitions of ControlNet and “sidecar”, the exact proof rows, and when each route is the right tool.
- Wan video: practical Wan2.2 T2V/I2V sizing, plain and masked prompt-guided A14B video-to-video, the natively ported Wan2.1-VACE-1.3B route (
wan-vace: reference-image object injection and learned mask conditioning with--vace-masked-region), the measured motion-fidelity ladder (strength vs gesture preservation, with a motion-preserving restyle recipe), the fps-resampling and audio copy-through contract with a playable proof, broader A14B target size families, full example commands, and included MP4/frame-strip assets. - Bernini-R 1.3B: experimental reference-to-video and video-edit routes, pinned BF16 runtime setup, measured memory, the committed official public parity bundle (full prompts and contact sheets per upstream example row), and task-specific recipes for many-reference binding and structure-changing edits.
- Spaceship snow workflow: reproducible model-backed T2I, I2I edit, multi-reference I2I, T2V A14B, and I2V A14B commands with included assets.
- Generation previews: step-wise previews rendered with published tiny autoencoders (
taef1,taef2), the--preview-decoder auto|tiny|fullcontract, the per-latent-space availability table, measured agreement against the full VAE, and the guarantee that final outputs are always full-VAE decoded. - Image upscaling: SeedVR2 command usage for image and video restoration, published 3B/7B q8/q4 package handles, shortest-edge and scale-factor sizing, the conservative safe-video profile, the validated June 21 five-second Eiffel
1xand2x3B/7B proof bundles plus timings/memory data, and real 5x image comparisons from a133x113source. - Image edit capabilities: image-edit plus generative reframe and outpaint contact sheets, exact model/package status, the Qwen Image Edit 2511 q8 masked-edit proof, the exact base Qwen q8 structured-control and control-inpaint proofs, the exact Z-Image Turbo q8 native-inpaint proof, the FLUX.2 Klein base source-model starship proof, and command logs for Qwen Image Edit, Qwen Image Edit 2509/2511, FLUX.2 Klein, Qwen control routes, Z-Image native inpaint, and latent I2I rows. FIBO Edit is unsupported through unified
mlxgen generate. - Reframe and outpaint:
--reframe-paddingand--outpaint-paddingworkflows, supported models, the historical mixed June 8 profile, the current FLUX.2 Klein base source-model starship proof, and the validation profile ids for canvas expansion workflows. - LoRA: route-specific capability fields, explicit adapter download, strict scale matching, model-card base-model compatibility, source/no-LoRA/with-LoRA validation, exact public proof rows for the current Qwen, Z-Image, FLUX.2, ERNIE, and Wan routes, and the current guidance that MLX-Gen q8 packages are the validated Lightning target rather than arbitrary external FP8 checkpoints.
- Model management: explicit download and prepare workflows, generation from local files, Bernini's pinned factored download and disk preflight, local package resolution, and Depth Pro downloads.
- Model recommendations: conservative starting picks for
18 GB,24 GB,32 GB,64 GB, and128+ GBMacs, using published MLX-Gen memory measurements rather than package size alone. - Quantization: current low-bit compatibility by model family, including the published package matrix, Bernini's BF16-only boundary, Bonsai ternary 2-bit support, SeedVR2 packages, Qwen/ERNIE policies, and Wan storage/runtime behavior.
- Hugging Face publishing: generated model cards, source license/access wording, default
AbstractFramework/<repo-name>usage, upload flow, and optional collection membership. - Python integration: route-resolved runtime planning/loading, Bernini's typed reference inputs, serial multi-output reuse, SeedVR2's direct-model boundary, and shared progress callbacks.
- Release: GitHub Release and PyPI trusted publishing workflow.
- FAQ: common questions about setup, memory versus disk, quantization, image/edit modes, SeedVR2, Wan, and Bernini.
- Troubleshooting: common setup, cache, local-path, routing, quantization, Bernini reference-fidelity, and Wan video problems with concrete fixes.
The top-level README remains the starting point for installation, model families, and project relationship details.
Project Documents¶
- Acknowledgements: upstream mflux credit, post-fork maintainership, and model/community acknowledgements.
- Changelog: release history and migration notes.
- Contributing: local development, checks, and pull-request expectations.
- Architecture Decision Records: durable validation and architecture policies.
- Security: vulnerability reporting and model/token safety guidance.
- Code of Conduct: participation expectations.