Best open source Image to Video CogVideoX1.5-5B-I2V is pretty decent and optimized for low VRAM
Best open source Image to Video CogVideoX1.5-5B-I2V is pretty decent and optimized for low VRAM machines with high resolution – native resolution is 1360px and up to 10 seconds 161 frames – audios generated with new open source audio model
Resources and Details for CogVideoX1.5–5B-I2V Image-to-Video Generation
This section provides a comprehensive overview of the resources, tools, and configurations I used when working with the CogVideoX1.5–5B-I2V model for image-to-video generation.
Video Tutorial and Installation Guides:
-
1-Click Installers: For streamlined setup, I’ve created 1-Click installers for Windows, RunPod, and Massed Compute environments. These are available at: https://www.patreon.com/posts/112848192. Note: These installers set up the model within a Python 3.11 virtual environment (VENV).
Model Repositories and Prompts:
Configuration and Optimizations:
-
Video Settings: I generated videos using 1360x768px resolution images at 16 FPS for 81 frames (resulting in approximately 5-second videos, including the initial frame).
-
Enabled Optimizations: I utilized the following optimizations recommended on the Hugging Face page:
-
pipe.enable_sequential_cpu_offload()
-
pipe.vae.enable_slicing()
-
pipe.vae.enable_tiling()
-
Quantization: I used int8_weight_only quantization. Note that TorchAO is required, and DeepSpeed works effectively on Windows with a Python 3.11 VENV.
Audio Generation:
-
MMAudio Model: For adding audio to the generated videos, I used the MMAudio model: https://github.com/hkchengrex/MMAudio
-
MMAudio Installers: 1-Click installers for MMAudio (Windows, RunPod, Massed Compute) are available at: https://www.patreon.com/posts/117990364. Note: These installers use a Python 3.10 VENV.
-
Prompting MMAudio: I used simple prompts for audio generation. Be aware that MMAudio may struggle when the input video contains human figures. In such cases, consider using text-to-audio alternatives.
VRAM Usage Observations:
I tested CogVideoX1.5–5B-I2V with various resolutions and frame counts to determine VRAM usage. Here are some of my findings (note that lower VRAM GPUs might still work, albeit slower):
-
512×288 (41 frames): ~7700 MB
-
576×320 (41 frames): ~7900 MB
-
576×320 (81 frames): ~8850 MB
-
704×384 (81 frames): ~8950 MB
-
768×432 (81 frames): ~10600 MB
-
896×496 (81 frames): ~12050 MB
-
960×528 (81 frames): ~12850 MB
-
1024×576 (81 frames): ~13900 MB
-
1280×720 (81 frames): ~17950 MB
-
1360×768 (81 frames): ~19000 MB
Gradio App:
Our Gradio application is highly advanced and functions flawlessly.