DiffSynth-Studio/MiniMax-H3-LoRA-LineartAnime

Anime Video Line Art Colorization (MiniMax-H3 LoRA)

This model is a LoRA fine-tuned on the video generation model MiniMax-H3, capable of generating exquisite anime visuals from input line art videos.

Examples

Prompts

Prompts can directly describe the visual content. The prompts used in the three examples above are as follows:

• Prompt 1: A shy, blushing girl with long blue hair in white clothes and a frosty headband, sitting against a glacial ice wall with a bashful expression, surrounded by floating ice shards and soft magical glow.
• Prompt 2: A shy, blushing girl with long black hair in a yellow top, white headband, and pink bow, sitting against a plain white wall with a gentle, bashful expression, softly and evenly lit from the front.
• Prompt 3: A shy, blushing girl with long red hair in a white top, black headband, and pink bow, sitting on a bed in a bedroom bathed in bright, golden sunset light. Warm orange and amber rays stream through the window, illuminating the scene with a radiant glow as her gentle, bashful expression is softly highlighted by the luminous evening atmosphere.

Alternatively, editing instructions can be used as prompts, allowing the model to determine the visual content autonomously:

• Editing prompt: Generate anime videos from line art outlines.

Inference

First, install DiffSynth-Studio:

git clone https://github.com/modelscope/DiffSynth-Studio.git
cd DiffSynth-Studio
pip install -e ".[all]"

import torch
from PIL import Image
from diffsynth.pipelines.minimax_h3_audio_video import MiniMaxH3Pipeline, ModelConfig
from diffsynth.utils.data.audio_video import write_video_audio, read_video_audio
from modelscope import dataset_snapshot_download

vram_config = {
    "offload_dtype": "disk",
    "offload_device": "disk",
    "onload_dtype": "disk",
    "onload_device": "disk",
    "preparing_dtype": torch.bfloat16,
    "preparing_device": "cuda",
    "computation_dtype": torch.bfloat16,
    "computation_device": "cuda",
}
pipe = MiniMaxH3Pipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="DiffSynth-Studio/MiniMax-H3-NF4", origin_file_pattern="minimax-h3-ref2va-nf4.safetensors", **vram_config),
        ModelConfig(model_id="DiffSynth-Studio/MiniMax-H3-NF4", origin_file_pattern="minimax-h3-text-encoder-nf4.safetensors", **vram_config),
        ModelConfig(model_id="DiffSynth-Studio/MiniMax-H3-NF4", origin_file_pattern="video_vae_nf4.safetensors", **vram_config),
        ModelConfig(model_id="DiffSynth-Studio/MiniMax-H3-NF4", origin_file_pattern="audio_vae_nf4.safetensors", **vram_config),
    ],
    processor_config=ModelConfig(model_id="MiniMax/MiniMax-H3", origin_file_pattern="Ref2VA/processor/"),
    vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 5,
)
lora = ModelConfig(model_id="DiffSynth-Studio/MiniMax-H3-LoRA-LineartAnime", origin_file_pattern="model.safetensors")
pipe.load_lora(pipe.dit, lora)

dataset_snapshot_download(
    "DiffSynth-Studio/MiniMax-H3-LoRA-LineartAnime",
    allow_file_pattern="assets/video_input.mp4",
    local_dir="data"
)

# The height and width must be consistent!
control_video, _, _ = read_video_audio("data/assets/video_input.mp4", height=768, width=1344, num_frames=90, fps=24, audio_sample_rate=32000)
prompt = "A shy, blushing girl with long blue hair in white clothes and a frosty headband, sitting against a glacial ice wall with a bashful expression, surrounded by floating ice shards and soft magical glow."
video, audio = pipe(
    prompt=prompt,
    height=768, width=1344, num_frames=90, num_inference_steps=20, seed=42,
    references=[
        {"type": "video", "video": control_video},
    ],
    ref_video_short_edge=768, ref_video_max_pixels=768*1344,
)
write_video_audio(
    video=video, audio=audio,
    output_path="output.mp4", fps=24, audio_sample_rate=32000,
)

Training

Please refer to the example code and documentation provided by DiffSynth-Studio.