---
license: other
license_name: minimax-h3-community-license-agreement
license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE
base_model:
- Comfy-Org/MiniMax-H3
tags:
- minimax-h3
- lora
- text-to-video
- style
- anime
- 2d
- cel-shading
- comfyui
library_name: ai-toolkit
pipeline_tag: text-to-video
---

# MiniMax H3 — 2D Anime Style LoRA (v1)

A flat **2D anime cel-shading** style adapter for [MiniMax H3](https://huggingface.co/MiniMaxAI/MiniMax-H3)
(FL2VA text-to-video): clean line art, flat cel shading, vibrant anime color work.

- **Trigger word:** `2danime` (lead your prompt with it, e.g. *"2danime style anime illustration
  of a girl walking through a city street at sunset, flat 2D anime cel shading, clean line art,
  vibrant colors"*)
- **Recommended strength:** 0.8–1.0
- **Works with:** FL2VA text-to-video; attach as a model-only LoRA in ComfyUI on the
  `minimax_h3_fl2va_pruned_int8_convrot` weights. Do **not** merge into the quantized checkpoint —
  load it as a live adapter.

## Training

- **Data:** 420 anime wallpaper stills sampled across the full history of
  [puruchinera/anime_wallpapers](https://huggingface.co/datasets/puruchinera/anime_wallpapers)
  (spread across date folders, 512px short side, filtered for aspect/size), captioned with the
  `2danime` trigger + style descriptors
  ([prep'd dataset](https://huggingface.co/datasets/akhaliq/h3-anime2d-style-train-v1))
- **Method:** ai-toolkit `minimax_h3` extension (FL2VA partition, pruned int8-ConvRot DiT), rank 16,
  single-latent-frame image training at 512px, `adamw8bit`, lr 1e-4, latents + text embeddings
  cached to disk, contrastive guidance loss (target 3.5) plus the frozen
  [ostris training adapter](https://huggingface.co/ostris/minimax_h3_training_adapter),
  `ignore_if_contains: ["adaln_proj"]`, audio not trained
- **Observed run:** 2,000 steps at ~1.2 s/step on a single A100 80 GB — 1h08m total wall-clock
  including setup and in-training sampling (≈ $2.85)

## Checkpoints

Checkpoints saved every 250 steps are in `checkpoints/` (steps 250–1750 + final 2000). Pick by
the previews in `samples/`, not by step count.

## Known limitations

- Trained on wallpapers: scenery and illustration style transfer strongly; character-focused
  shots (faces, close-ups) may be weaker since wallpapers skew toward wide scenes.
- The source pool is community-curated wallpaper art — occasional non-2D renders (3D-style
  wallpaper art) may have slipped into training; captions describe the flat 2D target style.
- The look transfers; anime **motion** (smears, limited animation timing) is not learned —
  motion stays base-H3.

## Samples

`samples/anime2d_h3_v1/samples/` holds in-training previews every 250 steps × 4 prompts
(schoolgirl street / knight cliff / cat windowsill / fighter jet).