nightmareai/cogvideo 🔢📝✓🖼️ → 🖼️

▶️ 32.8K runs 📅 Jul 2022 ⚙️ Cog v0.3.13+dev 🔗 GitHub 📄 Paper ⚖️ License

image-to-video text-to-video

About

Text-to-video generation

Example Output

Prompt:

"a black cat"

Output

Performance Metrics

760.52s Prediction Time

1789.86s Total Time

All Input Parameters

{
  "seed": "-1",
  "prompt": "a black cat",
  "translate": true,
  "both_stages": true,
  "use_guidance": true
}

Input Parameters

seed Type: integerDefault: -1Range: -1 - 100000: Seed (-1 to use a random seed)
prompt (required) Type: string: Prompt
translate Type: booleanDefault: true: Translate prompt from English to Simplified Chinese (required if not entering Chinese text)
both_stages Type: booleanDefault: true: Run both stages (uncheck to run more quickly and output only a few frames)
image_prompt Type: string: Starting image (optional, prompt has little effect when used)
use_guidance Type: booleanDefault: true: Use stage 1 guidance (recommended)

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

2022-07-26 06:02:08 DEBUG    Starting new HTTPS connection (1): translate.google.com:443
2022-07-26 06:02:08 DEBUG    https://translate.google.com:443 "GET /m?tl=zh-CN&sl=en&q=a+black+cat HTTP/1.1" 200 None
2022-07-26 06:02:08 DEBUG    moving stage 2 model to cpu
2022-07-26 06:02:08 DEBUG    moving stage 1 model to cuda
2022-07-26 06:02:12 DEBUG    moving in model1 takes time: 3.75
2022-07-26 06:02:12 INFO     [Generating First Frame with CogView2]Raw text: 一只黑猫 高清摄影
2022-07-26 06:02:51 INFO     [First Frame]Taken time 39.40

2022-07-26 06:02:51 INFO     [Stage1: Generating Subsequent Frames, Frame Rate 1.0]
raw text: 一只黑猫 视频
2022-07-26 06:02:51 DEBUG    Using Guidance In Inference
2022-07-26 06:02:51 DEBUG    Limit spatial-channel's mem to current frame
2022-07-26 06:08:17 DEBUG    Attempting to acquire lock 140517844067568 on /root/.icetk_models/ice_image.pt.lock
2022-07-26 06:08:17 DEBUG    Lock 140517844067568 acquired on /root/.icetk_models/ice_image.pt.lock
2022-07-26 06:08:17 DEBUG    Attempting to release lock 140517844067568 on /root/.icetk_models/ice_image.pt.lock
2022-07-26 06:08:17 DEBUG    Lock 140517844067568 released on /root/.icetk_models/ice_image.pt.lock

Save to:  /tmp/tmph7a4dbpv/output/stage1
2022-07-26 06:08:24 INFO     CogVideo Stage1 completed. Taken time 371.81

2022-07-26 06:08:24 DEBUG    moving stage 1 model to cpu
2022-07-26 06:08:35 DEBUG    moving stage-2 model to cuda
2022-07-26 06:08:39 DEBUG    moving in stage-2 model takes time: 4.04
2022-07-26 06:08:39 INFO     [Stage2: Generating Frames, Frame Rate 2]
raw text: 一只黑猫
2022-07-26 06:08:39 DEBUG    Limit spatial-channel's mem to current frame
2022-07-26 06:10:16 INFO     Duration 2.00, Taken time 96.67

2022-07-26 06:10:16 INFO     [Stage2: Generating Frames, Frame Rate 4]
raw text: 一只黑猫
2022-07-26 06:10:16 DEBUG    Limit spatial-channel's mem to current frame

Version Details

Version ID: 00b1c7885c5f1d44b51bcb56c378abc8f141eeacf94c1e64998606515fe63a8d
Version Created: July 27, 2022

Run on Replicate →