Cogvideox I2V Locobot

🚀 CogVideoX LoRA - BelGio13/cogvideoX-I2V-locobot

這是用於圖像到視頻轉換的CogVideoX LoRA模型，能夠基於輸入圖像生成高質量的視頻。

🚀 快速開始

你可以按照以下步驟使用該模型：

1. 下載模型的 *.safetensors LoRA 文件，可在 Files & versions 標籤頁 進行下載。
2. 使用以下代碼示例，結合 🧨 diffusers 庫 來運行模型。

import torch
from diffusers import CogVideoXImageToVideoPipeline
from diffusers.utils import load_image, export_to_video

pipe = CogVideoXImageToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b-I2V", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("BelGio13/cogvideoX-I2V-locobot", weight_name="pytorch_lora_weights.safetensors", adapter_name="cogvideox-i2v-lora")

# The LoRA adapter weights are determined by what was used for training.
# In this case, we assume `--lora_alpha` is 32 and `--rank` is 64.
# It can be made lower or higher from what was used in training to decrease or amplify the effect
# of the LoRA upto a tolerance, beyond which one might notice no effect at all or overflows.
pipe.set_adapters("cogvideox-i2v-lora", [32 / 64])

image = load_image("/path/to/image")
video = pipe(image=image, "", guidance_scale=6, use_dynamic_cfg=True).frames[0]
export_to_video(video, "output.mp4", fps=8)

更多細節，包括 LoRA 的加權、合併和融合等操作，請查看 diffusers 中加載 LoRA 的文檔。

✨ 主要特性

• 這些是 BelGio13/cogvideoX-I2V-locobot 的 LoRA 權重，適用於 THUDM/CogVideoX-5b-I2V 基礎模型。
• 權重使用 CogVideoX Diffusers 訓練器 進行訓練。
• 文本編碼器未啟用 LoRA。

📦 安裝指南

暫未提供具體安裝步驟，可參考上述快速開始部分結合 diffusers 庫使用。

💻 使用示例

基礎用法

import torch
from diffusers import CogVideoXImageToVideoPipeline
from diffusers.utils import load_image, export_to_video

pipe = CogVideoXImageToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b-I2V", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("BelGio13/cogvideoX-I2V-locobot", weight_name="pytorch_lora_weights.safetensors", adapter_name="cogvideox-i2v-lora")

# The LoRA adapter weights are determined by what was used for training.
# In this case, we assume `--lora_alpha` is 32 and `--rank` is 64.
# It can be made lower or higher from what was used in training to decrease or amplify the effect
# of the LoRA upto a tolerance, beyond which one might notice no effect at all or overflows.
pipe.set_adapters("cogvideox-i2v-lora", [32 / 64])

image = load_image("/path/to/image")
video = pipe(image=image, "", guidance_scale=6, use_dynamic_cfg=True).frames[0]
export_to_video(video, "output.mp4", fps=8)

高級用法

暫未提供高級用法示例。

📚 詳細文檔

模型描述

這些是 BelGio13/cogvideoX-I2V-locobot 的 LoRA 權重，用於 THUDM/CogVideoX-5b-I2V 模型。權重使用 CogVideoX Diffusers 訓練器 進行訓練，且文本編碼器未啟用 LoRA。

預期用途與限制

如何使用

# TODO: add an example code snippet for running this diffusion pipeline

限制和偏差

[TODO: provide examples of latent issues and potential remediations]

訓練細節

[TODO: describe the data used to train the model]

📄 許可證

請遵守 此處 描述的許可條款。

📦 模型信息