🚀 扁平色彩風格模型
本項目的扁平色彩風格模型專注於生成無明顯線條、色彩扁平且深度感較弱的圖像和視頻,為圖像與視頻生成領域帶來獨特的視覺體驗。
🚀 快速開始
觸發詞使用
- 使用
flat color
觸發圖像生成。
- 使用
no lineart
觸發圖像生成。
模型下載
本模型的權重以 Safetensors 格式提供,可在 Files & versions 標籤頁 中下載。
✨ 主要特性
- 獨特風格:基於無明顯線條、扁平色彩和弱深度感的圖像進行訓練,生成具有獨特風格的圖像和視頻。
- 廣泛應用:適用於多種場景,如虛擬主播形象、動漫風格視頻等。
📦 安裝指南
加載 LoRA 時,使用 LoraLoaderModelOnly
節點,並使用 fp16
的 wan2.1_t2v_1.3B_fp16.safetensors
。
💻 使用示例
基礎用法
可在 ComfyUI_examples/wan/#text-to-video 中查看文本到視頻的預覽示例。
以下是一些示例輸入及對應輸出:
示例 1
輸入文本:flat color, no lineart, blending, negative space, artist:[john kafka|ponsuke kaikai|hara id 21|yoneyama mai|fuzichoco], 1girl, hoshimachi suisei, virtual youtuber, blue hair, side ponytail, cowboy shot, black shirt, star print, off shoulder, outdoors, starry sky, wariza, looking up, half-closed eyes, black sky, live2d animation, upper body, high quality cinematic video of a woman sitting under the starry night sky. The Camera is steady, This is a cowboy shot. The animation is smooth and fluid.
負提示詞:bad quality video,色調豔麗,過曝,靜態,細節模糊不清,字幕,風格,作品,畫作,畫面,靜止,整體發灰,最差質量,低質量,JPEG壓縮殘留,醜陋的,殘缺的,多餘的手指,畫得不好的手部,畫得不好的臉部,畸形的,毀容的,形態畸形的肢體,手指融合,靜止不動的畫面,雜亂的背景,三條腿,背景人很多,倒著走
輸出:[images/ComfyUI_00455_.webp](images/ComfyUI_00455_.webp)
示例 2
輸入文本:flat color, no lineart, blending, negative space, artist:[john kafka|ponsuke kaikai|hara id 21|yoneyama mai|fuzichoco], 1girl, sakura miko, pink hair, cowboy shot, white shirt, floral print, off shoulder, outdoors, cherry blossom, tree shade, wariza, looking up, falling petals, half-closed eyes, white sky, clouds, live2d animation, upper body, high quality cinematic video of a woman sitting under a sakura tree. Dreamy and lonely, the camera close-ups on the face of the woman as she turns towards the viewer. The Camera is steady, This is a cowboy shot. The animation is smooth and fluid.
負提示詞:bad quality video,色調豔麗,過曝,靜態,細節模糊不清,字幕,風格,作品,畫作,畫面,靜止,整體發灰,最差質量,低質量,JPEG壓縮殘留,醜陋的,殘缺的,多餘的手指,畫得不好的手部,畫得不好的臉部,畸形的,毀容的,形態畸形的肢體,手指融合,靜止不動的畫面,雜亂的背景,三條腿,背景人很多,倒著走
輸出:[images/ComfyUI_00469_.webp](images/ComfyUI_00469_.webp)
📚 詳細文檔
模型描述
本模型基於 Wan-AI/Wan2.1-T2V-1.3B-Diffusers 基礎模型進行訓練。相關內容轉載自 CivitAI。
訓練配置
本模型使用 diffusion-pipe 進行訓練,以下是詳細的訓練配置文件:
dataset.toml
resolutions = [512]
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 7
frame_buckets = [1]
[[directory]]
path = '/mnt/d/huanvideo/training_data/images'
num_repeats = 5
resolutions = [720]
frame_buckets = [1]
[[directory]]
path = '/mnt/d/huanvideo/training_data/videos'
num_repeats = 5
resolutions = [512]
frame_buckets = [6, 28, 31, 32, 36, 42, 43, 48, 50, 53]
config.toml
output_dir = '/mnt/d/wan/training_output'
dataset = 'dataset.toml'
epochs = 50
micro_batch_size_per_gpu = 1
pipeline_stages = 1
gradient_accumulation_steps = 4
gradient_clipping = 1.0
warmup_steps = 100
eval_every_n_epochs = 5
eval_before_first_step = true
eval_micro_batch_size_per_gpu = 1
eval_gradient_accumulation_steps = 1
save_every_n_epochs = 5
checkpoint_every_n_minutes = 30
activation_checkpointing = true
partition_method = 'parameters'
save_dtype = 'bfloat16'
caching_batch_size = 1
steps_per_print = 1
video_clip_mode = 'single_middle'
[model]
type = 'wan'
ckpt_path = '../Wan2.1-T2V-1.3B'
dtype = 'bfloat16'
transformer_dtype = 'float8'
timestep_sample_method = 'logit_normal'
[adapter]
type = 'lora'
rank = 32
dtype = 'bfloat16'
[optimizer]
type = 'adamw_optimi'
lr = 5e-5
betas = [0.9, 0.99]
weight_decay = 0.02
eps = 1e-8
📄 許可證
本項目採用 Apache-2.0 許可證。