Model Card
Here is a detailed description of how cogkit supports models.
All training requirements must be strictly followed as specified in the table below, including resolution, number of frames, prompt token limit, and video length requirements.
CogVideo
| Model Name | CogVideoX1.5-5B | CogVideoX1.5-5B-I2V | CogVideoX-2B | CogVideoX-5B | CogVideoX-5B-I2V |
|---|---|---|---|---|---|
| Release Date | November 8, 2024 | November 8, 2024 | August 6, 2024 | August 27, 2024 | September 19, 2024 |
| Video Resolution (W * H) | 1360 * 768 | Min(W, H) = 768 768 ≤ Max(W, H) ≤ 1360 Max(W, H) % 16 = 0 | 720 * 480 | ||
| Number of Frames | Should be 16N + 1 where N ≤ 10 (default 81) | Should be 8N + 1 where N ≤ 6 (default 49) | |||
| Prompt Language | English | ||||
| Prompt Token Limit | 224 Tokens | 226 Tokens | |||
| Video Length | 5 seconds or 10 seconds | 6 seconds | |||
| Frame Rate | 16 frames / second | 8 frames / second | |||
| Download Link (Diffusers) | 🤗 HuggingFace 🤖 ModelScope 🟣 WiseModel | 🤗 HuggingFace 🤖 ModelScope 🟣 WiseModel | 🤗 HuggingFace 🤖 ModelScope 🟣 WiseModel | 🤗 HuggingFace 🤖 ModelScope 🟣 WiseModel | 🤗 HuggingFace 🤖 ModelScope 🟣 WiseModel |
CogView
| Model Name | CogView4-6B (Latest) |
|---|---|
| Release Date | March 4, 2025 |
| Resolution | 512 ≤ (W, H) ≤ 2048 H * W ≤ 2^21 Max(W, H) % 32 = 0 |
| Prompt Language | English，简体中文 |
| Prompt Token Limit | 1024 Tokens (GLM-4-9B) |
| Download Link (Diffusers) | 🤗 HuggingFace 🤖 ModelScope 🟣 WiseModel |