You can deploy this model and start earning money today!

AnimeLoom/
README

Views

No views yet

AnimeLoom

Open-source character LoRAs and tooling for face-consistent anime video generation.

AnimeLoom is a text-to-anime-video pipeline focused on the hardest part of long-form anime generation: keeping the same character's face the same across every shot.

This organization hosts the character LoRAs used by the AnimeLoom pipeline on GitHub.

Character LoRAs

Character	Series	Repo
Sakura Haruno	Naruto	AnimeLoom/sakura-haruno
Denji	Chainsaw Man	AnimeLoom/denji
Yuki Nagato	The Melancholy of Haruhi Suzumiya	AnimeLoom/yuki-nagato

Every LoRA ships two adapters in one repo:

sdxl/ — for Animagine XL 3.1, used by AnimeLoom's identity-keyframe stage
sd15/ — for DreamShaper 8, for lightweight AnimateDiff workflows

All adapters are LoRA rank 32, trained with PEFT.

The pipeline

AnimeLoom is a Director-Orchestrated pipeline that turns a text story into a multi-shot anime video with consistent character identity.

text story
   ↓
Story Decomposer (Gemini → Claude)        →  shot script
   ↓
SDXL + character LoRA + IP-Adapter        →  identity keyframe per shot   (Phase 2)
   ↓
Wan2.2 I2V                                →  motion driving clip          (Phase 3a)
   ↓
Wan2.2-Animate face-lock                  →  face from keyframe pasted
                                              onto motion clip            (Phase 3b)
   ↓
RIFE + Real-ESRGAN + GFPGAN               →  temporal/spatial upscale,
                                              anime face restore           (Phase 4)
   ↓
Cross-dissolve assembly                   →  final 24fps video

Why face-lock matters

The "Animate" stage at Phase 3b is the moat. Per community testing, Wan2.2-Animate-14B achieves an 89% usable rate versus AnimateDiff's 71% and commercial APIs' ~78%. Combined with character-specific LoRAs trained for the SDXL identity stage, AnimeLoom can keep a character recognizably "themselves" across every shot of a multi-shot scene — the part most open-source pipelines struggle with.

Quick start

Train your own character LoRA, or use one from this org:

python

import torch
from diffusers import StableDiffusionXLPipeline
from peft import PeftModel

pipe = StableDiffusionXLPipeline.from_pretrained(
    "cagliostrolab/animagine-xl-3.1",
    torch_dtype=torch.float16,
).to("cuda")

# Load any AnimeLoom character LoRA
pipe.unet = PeftModel.from_pretrained(
    pipe.unet,
    "AnimeLoom/sakura-haruno",   # or AnimeLoom/denji, AnimeLoom/yuki-nagato
    subfolder="sdxl",
)

img = pipe(
    "1girl, sakura haruno, pink hair, cherry blossom forest, anime, masterpiece",
    num_inference_steps=28,
    guidance_scale=6.5,
    height=1024, width=1024,
).images[0]
img.save("out.png")

For the full text-to-video pipeline, see the AnimeLoom RunPod notebook.

License

All character LoRAs in this org are released under OpenRAIL++, inheriting from their base models (Animagine XL 3.1 / DreamShaper 8). The AnimeLoom pipeline code on GitHub is MIT licensed.

Contributing

Want to add a character? The training script is in agents/character/trainer.py. Recommended dataset: 15-30 clean anime reference images of the character at 512 or 1024 resolution.

Issues, PRs, and new character requests: GitHub Issues.

AnimeLoom/README