Anima Adapter Loader

anima_lora

New (alpha): MOSS-Image LoRA. Train LoRAs for OpenMOSS's 5B MOSS-Image on a 16 GB card, with Spectrum sampling (2.6×) — make gui-moss. A separate line from Anima; flags and defaults may still change.

📖 Guidebook: English · 한국어 · 日本語 · 中文

<p align="center"> <img src="docs/gui.png" alt="Anima LoRA GUI — training-config editor with method/variant picker, inline method help, and live training monitor" width="900"> </p>

LoRA / T-LoRA training and inference engine for the Anima diffusion model (DiT, flow matching).

Install

One line: installs uv, picks NVIDIA CUDA or AMD ROCm on Windows, fetches the latest release, runs uv sync and opens the GUI (no git needed).

# Linux / macOS
curl -LsSf https://github.com/sorryhyun/anima_lora/releases/latest/download/install.sh | sh

# Windows (PowerShell)
irm https://github.com/sorryhyun/anima_lora/releases/latest/download/install.ps1 | iex

Sign in to Hugging Face and download models from the GUI. Requirements, checksum-verified and pinned installs, and the manual clone path: Advanced installation.

Features

Diagrams for every method: docs/structure_images/, prose walkthroughs in docs/structure/.

Fast training

13.4 GB peak VRAM · 1.1 s/step on an RTX 5060 Ti (rank 32, 1 MP). Per-block torch.compile with a dynamic sequence axis (one graph per token-count tier), fused QKV/KV, an activation memory budget instead of gradient checkpointing, and a compile-clean hot path. Details: for_compile.md.

On by default

| Feature | Doc | |---|---| | LoRA with SVD-Down init (down_init = "weight_svd") | svd-down-lora.md | | T-LoRA timestep rank masking | timestep_mask.md | | Channel scaling (channel_scaling_alpha = 0.5, Adam-specific) | channel_scaling.md | | Free-fit native-aspect bucketing (the only resize mode) | for_compile.md | | AdaLN low-rank delta (train_adaln, provisional) | adaln.md | | CJK vocab pack (Japanese text in captions and images) | cjk_vocab_pack.md |

LoRA and T-LoRA bake losslessly into a standalone DiT: make merge [ADAPTER_DIR=… MULTIPLIER=0.8].

Inference stacks

Training-free; each composes with any checkpoint. Overview: docs/inference/.

| Method | Doc | |---|---| | Spectrum — feature forecasting, ≈1.75× (ComfyUI node) | spectrum.md | | SMC-CFG — sliding-mode CFG correction | smc_cfg.md | | Modulation guidance | mod-guidance.md | | SPD — progressive multi-resolution sampling | spd.md | | Embedding inversion | invert.md |

Training stacks

| Method | Doc | |---|---| | HydraLoRA — multi-head LoRA with per-sample routing (ComfyUI node) | hydra-lora.md | | Turbo — DP-DMD few-step distillation, output is a normal LoRA (4-step student) | turbo.md | | Soft Tokens (experimental) | soft_tokens.md | | DirectEdit + Anima Tagger (experimental) | directedit_editing_v3.md | | EasyControl (experimental) | easycontrol.md |

Want to contribute? EasyControl adapters (canny / depth / pose / …, one PR per control type) — see CONTRIBUTING.md → Priority areas.

Usage

make gui                  # config editor + dataset browser + training monitor
make preprocess           # resize + cache latents / text embeddings
make lora                 # or PRESET=low_vram make lora
make test                 # sample with the latest LoRA

Config chain: configs/base.toml → configs/presets.toml[<preset>] → configs/methods/<method>.toml → CLI args. Flags: training.md, inference.md. All docs: docs/.

Advanced installation

Requirements: NVIDIA Ampere or newer with driver ≥595 (Python 3.13 + PyTorch 2.14 + CUDA 13.2). Windows ROCm targets RDNA 4 (gfx1200 / gfx1201; certified on RX 9060 XT / 9070 XT) with PyTorch 2.13 + ROCm 10.0.

The installer writes to ./anima_lora/ (ANIMA_DIR overrides) and, on Windows, adds an "Anima LoRA GUI" desktop shortcut. Force the backend with $env:ANIMA_BACKEND='cuda' or 'rocm'. Pin a release with ANIMA_VERSION=<tag>. Update in place with make update.

<details> <summary><b>Safer install</b> — verify the script before running</summary>

Every release ships a checksums.txt (SHA-256 of the installers and source archives).

# Linux / macOS
curl -fLO https://github.com/sorryhyun/anima_lora/releases/latest/download/install.sh
curl -fLO https://github.com/sorryhyun/anima_lora/releases/latest/download/checksums.txt
grep install.sh checksums.txt | sha256sum -c -    # must print "install.sh: OK"
less install.sh
sh install.sh

# Windows (PowerShell)
iwr https://github.com/sorryhyun/anima_lora/releases/latest/download/install.ps1 -OutFile install.ps1
iwr https://github.com/sorryhyun/anima_lora/releases/latest/download/checksums.txt -OutFile checksums.txt
(Get-FileHash install.ps1 -Algorithm SHA256).Hash.ToLower()   # compare against checksums.txt
notepad install.ps1
powershell -ExecutionPolicy Bypass -File .\install.ps1

</details>

Manual (from a clone)

uv sync                                                    # CUDA (default, every platform)
uv sync --no-group cuda-windows --group rocm-windows       # Windows AMD only
uv sync --no-default-groups --group torch-213              # older torch (or torch-212)

hf auth login             # or sign in from the GUI
make download-models      # DiT, TE, VAE, PE-Spatial, CJK vocab pack, tagger, tag DB → models/
make download-list        # installed vs missing; SAM3 and OCR are opt-in

• ROCm users repeat the same --group flags on every later manual uv sync. To keep an opt-in torch across updates, run ANIMA_TORCH=2.13 make update once.
• The manual CUDA path does not install the CUDA 13.2 toolkit that torch.compile / Triton needs: see guidebook appendix C.
• Install with uv sync against the committed uv.lock, not pip install: pip ignores uv's index strategy and the prebuilt flash-attn wheels.

License

Toolkit code: MIT.

Portions are derived from kohya-ss/sd-scripts (Apache License 2.0) and remain under it — full text in LICENSE-APACHE, attribution and a statement of modifications in NOTICE. Thanks to kohya-ss and the sd-scripts contributors.

Anima / CircleStone base model weights ship under the CircleStone Labs Non-Commercial License v1.0 and are not relicensed by this repo. Any LoRA, fine-tune, or merged checkpoint trained from them is a Derivative and inherits the non-commercial terms. See NOTICE.