Skip to main content
Miles-diffusion is currently a standalone repository built on Miles’ design philosophy, focused on RL post-training for image and video diffusion models. sglang-diffusion serves the rollout, and the DiT trains under FSDP2 on a backend that co-evolves with Miles’ own. Models load from a diffusers pipeline, or from a native package when a family brings its own modeling. Shipped recipes carry explicit verification levels. Custom rewards, losses, and rollout functions plug in through flags.

​
Core features

  • Verified Recipes for Latest Diffusion Models. Launchers for Wan2.2-T2V-A14B, Qwen-Image, LTX-2.3, Cosmos3-Nano, and SD3.5. TrainPipelineConfig allows for easy model support.
  • Quality control on three fronts. Deterministic mode supports bit-for-bit comparisons for recipes covered by committed E2E standards; sglang-side monkey patches reduce train/rollout mismatches; and an FSDP2 param-dtype patch provides per-parameter fp32 control under the mixed-precision policy. See Deterministic Training and Dtype Control.
  • SFT, DiffusionNFT, and Flow-GRPO under one trainer. The loss type, training-batch preparation, rollout function, and reward function are all replaceable components, so integrating a new algorithm — or swapping in your own customized component — is easy.
  • Sglang native. Rollout runs on the inference engine itself — the sglang-diffusion serving stack — with RL support and optimizations living engine-side. An optional curated set of monkey patches aligns selected engine operations with the training-side forward.
  • Multiple parallelisms. The rollout engines scale with tensor and sequence parallelism to support large models and very long contexts; training scales with USP (Ulysses × Ring), built from each family’s diffusers _cp_plan — or a self-written one — for agile model integration.
  • LoRA training support. With --lora-ipc-weight-sync, PEFT LoRA on the FSDP2 actor ships only lora_A/lora_B pairs to colocated rollout engines over CUDA IPC and merges them engine-side. See LoRA Training and Weight Sync.

​
Supported models

Each model links to its recipe page; see verification levels. Validated models also appear in the Miles model list.

​
Feature support matrix

  • ✅ Recipe-backed — exercised by a canonical recipe in scripts/ or a CI test.
  • 🟡 Implemented — the code path exists, but no shipped recipe or test covers this combination yet.
  • ❌ Not supported — no working code path for this combination today.

​
Start here

  1. Installation — Docker image, pinned dependency versions, bare-metal setup.
  2. Quick Start — a working Flow-GRPO run on SD3.5 with 2 GPUs.
  3. Core Concepts — the four objects in every miles-diffusion job and the loop that connects them.
  4. Launch Scripts — every argument group in a launch script, annotated.
  5. Rewards — built-in reward models and custom reward hooks.
  6. Model guides — per-model config and recipes, starting from the supported models table above.

​
Contribute