1580158
/
sd-webui-text2video
mirror of https://github.com/kabachuha/sd-webui-text2video.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

a bit better wording about saving models

pull/193/head
kabachuha 2023-07-03 12:05:18 +03:00 committed by GitHub
parent 2396dcf7c1
commit 3f4a109a69
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/t2v_helpers/args.py
View File

@ -13,7 +13,7 @@ from modules.shared import opts
welcome_text_videocrafter = '''- Download pretrained T2V models via <a style="color:SteelBlue" href="https://drive.google.com/file/d/13ZZTXyAKM3x0tObRQOQWdtnrI2ARWYf_/view?usp=share_link">this link</a>, and put the model.ckpt in models/VideoCrafter/model.ckpt. Then use the same GUI pipeline as ModelScope does.
'''
welcome_text_modelscope = '''- Put your models to stable-diffusion-webui/models/text2video. Make sure you have a text file named 'configuration.json' in the downloaded models folders (click on the ⬇️ character to the right, don't save via right-click). Recommended requirements start at 6 GBs of VRAM.
welcome_text_modelscope = '''- Put your models to stable-diffusion-webui/models/text2video, each full model should have its own folder. A model consists of four parts: `VQGAN_autoencoder.pth`, `configuration.json`, `open_clip_pytorch_model.bin` and `text2video_pytorch_model.pth`. Make sure `configuration.json` is a text JSON file and not a saved HTML webpage (click on the ⬇️ character to the right, don't save via right-click). Recommended requirements start at 6 GBs of VRAM.
<a style="color:SteelBlue" href="https://github.com/kabachuha/sd-webui-text2video#prominent-fine-tunes">A list of prominent fine-tunes</a> is a good starting point for models search.