Comments (13)
Try setting "parser.add_argument("--pretrained_model_path", type=str, default="models/StableDiffusion/stable-diffusion-v1-5.safetensors",) " default path to "models/StableDiffusion". It should solve your problem.
from animatediff.
models/StableDiffusion
worked for me. it resolved all model path issues, the other recommendations didn't work. thanks aartykov
Error caused by path mismatch,
in code : parser.add_argument("--pretrained_model_path", type=str, default="models/StableDiffusion/stable-diffusion-v1-5",)
but in file: StableDiffusion name
Need to specify the correct path
like this
from animatediff.
Configured all afternoon and still can't solve the problem, is this something you don't want people to use?
from animatediff.
same problem
from animatediff.
models/StableDiffusion
worked for me. it resolved all model path issues, the other recommendations didn't work. thanks aartykov
from animatediff.
错误原因是:手动下的配置文件浏览器会自动修改名字(添加前缀),如tokenizer文件夹中的vocab.json被修改为“tokenizer_vocab.json”。(这个前缀就是所在文件夹的名字)
解决办法:手动修改回去就可以了。亲测可用。
官方代码没有问题的,不用修改。
from animatediff.
其它路径这样子,修写。在win10下面。
>>> create validation pipeline >>>
# tokenizer = CLIPTokenizer.from_pretrained(args.pretrained_model_path, subfolder="tokenizer")
tokenizer = CLIPTokenizer.from_pretrained("G:\\AI\\AnimateDiff\\models\\StableDiffusion\\tokenizer\\")
# text_encoder = CLIPTextModel.from_pretrained(args.pretrained_model_path, subfolder="text_encoder")
text_encoder = CLIPTextModel.from_pretrained("G:\\AI\\AnimateDiff\\models\\StableDiffusion\\text_encoder\\")
# vae = AutoencoderKL.from_pretrained(args.pretrained_model_path, subfolder="vae")
vae = AutoencoderKL.from_pretrained("G:\\AI\\AnimateDiff\\models\\StableDiffusion\\vae\\")
# unet = UNet3DConditionModel.from_pretrained_2d(args.pretrained_model_path, subfolder="unet", unet_additional_kwargs=OmegaConf.to_container(inference_config.unet_additional_kwargs))
unet = UNet3DConditionModel.from_pretrained_2d("G:\\AI\\AnimateDiff\\models\\StableDiffusion\\unet\\", unet_additional_kwargs=OmegaConf.to_container(inference_config.unet_additional_kwargs))
from animatediff.
same problem
青龙大佬,改文件animate.py,约是第150行。
parser.add_argument("--pretrained_model_path", type=str, default="models/StableDiffusion/stable-diffusion-v1-5.safetensors",)
from animatediff.
@RexLeeGrey couldn't agree more. I appreciate the work but the instructions are sorely lacking and so many issues without solutions.
I've been at it for 3 days and still can't get it figured out. Running WSL2 and every single time I solve one error there is another.
Haven't had this much trouble with any other app. :/
from animatediff.
Please use the configuration file to generate it directly, do not use Webui.
from animatediff.
其它路径这样子,修写。在win10下面。
>>> create validation pipeline >>>
创建验证管道 >>>
# tokenizer = CLIPTokenizer.from_pretrained(args.pretrained_model_path, subfolder="tokenizer") tokenizer = CLIPTokenizer.from_pretrained("G:\\AI\\AnimateDiff\\models\\StableDiffusion\\tokenizer\\") # text_encoder = CLIPTextModel.from_pretrained(args.pretrained_model_path, subfolder="text_encoder") text_encoder = CLIPTextModel.from_pretrained("G:\\AI\\AnimateDiff\\models\\StableDiffusion\\text_encoder\\") # vae = AutoencoderKL.from_pretrained(args.pretrained_model_path, subfolder="vae") vae = AutoencoderKL.from_pretrained("G:\\AI\\AnimateDiff\\models\\StableDiffusion\\vae\\") # unet = UNet3DConditionModel.from_pretrained_2d(args.pretrained_model_path, subfolder="unet", unet_additional_kwargs=OmegaConf.to_container(inference_config.unet_additional_kwargs)) unet = UNet3DConditionModel.from_pretrained_2d("G:\\AI\\AnimateDiff\\models\\StableDiffusion\\unet\\", unet_additional_kwargs=OmegaConf.to_container(inference_config.unet_additional_kwargs))
it work,thanks
from animatediff.
这个
it works for me, thanks!!!
from animatediff.
错误原因是:手动下的配置文件浏览器会自动修改名字(添加前缀),如tokenizer文件夹中的vocab.json被修改为“tokenizer_vocab.json”。(这个前缀就是所在文件夹的名字) 解决办法:手动修改回去就可以了。亲测可用。 官方代码没有问题的,不用修改。
it works for me, thanks!!!
from animatediff.
Related Issues (20)
- How to generate a gif image with pure green background? HOT 2
- Reproducing inference with depth maps
- Asking for image layer in Unet training HOT 1
- difference between finetuning the unet's image layers and training motion modules
- How to train Sparsecontrol?
- Any plan to support Apple M1/M2/M3 chips ? HOT 1
- RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
- motion module not in drop down list HOT 1
- update request
- AnimateDiff插件里面 Motion module 是空的 HOT 1
- How to reproduce demo in SparseCtrol, e.g., Keyframe and Video Interpolation, Video Prediction
- About temporal_position_encoding HOT 1
- The Code Gets Stuck at 0% HOT 1
- Gradio App is broken HOT 2
- Port to InvokeAI
- Problems for Motion LoRA training and inference
- Number of frames in training and inference
- Can't install torchaudio 0.13.1 HOT 14
- Error
- AttributeError: 'VersatileAttention' object has no attribute 'reshape_heads_to_batch_dim'
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from animatediff.