Comments (4)
this is the structure, as same as you, it is 4.17 gb.
class AudioLDM2ModelPredictor: def __init__(self): from diffusers import AudioLDM2Pipeline self.device = "cuda" if torch.cuda.is_available() else "cpu" torch_dtype = torch.float16 if self.device == "cuda" else torch.float32 # Use snapshot_download to manage the model download/cache self.model_path = snapshot_download("cvssp/audioldm2", local_dir=files_for_audio_model, force_download=False, # Set to True to always download local_files_only=False, # Download if not available locally use_auth_token=False, # Set to True if using a private model local_dir_use_symlinks="auto", # Auto-manage symlinks ignore_patterns=["*.bin", "*.jpg", "*.png"]) # Ignore unrelated files self.pipeline = AudioLDM2Pipeline.from_pretrained(self.model_path, torch_dtype=torch_dtype).to(self.device) self.generator = torch.Generator(self.device)change above code with this inside
custom_nodes/ComfyUI_VLM_nodes/nodes/audioldm2.py
class AudioLDM2ModelPredictor: def __init__(self): from diffusers import AudioLDM2Pipeline self.device = "cuda" if torch.cuda.is_available() else "cpu" torch_dtype = torch.float16 if self.device == "cuda" else torch.float32 # Use snapshot_download to manage the model download/cache self.model_path = files_for_audio_model self.pipeline = AudioLDM2Pipeline.from_pretrained(self.model_path, torch_dtype=torch_dtype).to(self.device) self.generator = torch.Generator(self.device)
Thank you very much for the author's guidance, according to your setting is successful! One reason for the installation failure is the local path setting, and another reason is that the downloaded configuration file name is not the same as his program, such as the language model folder in the configuration file is config.json, and the download from huggingface is language_model_config.json
from comfyui_vlm_nodes.
if you are sure about you download the all of the files. change local_files_only=True
in the audiolmd2.py
inside ComfyUI_VLM_nodes/nodes
folder
from comfyui_vlm_nodes.
if you are sure about you download the all of the files. change
local_files_only=True
in theaudiolmd2.py
insideComfyUI_VLM_nodes/nodes
folder
Yes, I downloaded all files related to audioldm2, but I still can't run this node. The file structure on hugging face is maintained in the folder "files_for_audioldm2". Can u share the structures and content of this folder, plz?
ps, even though I rewrote the option of "local_files_only", it didn't work.
The error:
Cannot find an appropriate cached snapshot folder for the specified revision on the local disk and outgoing traffic has been disabled. To enable repo look-ups and downloads online, pass 'local_files_only=False' as input.
from comfyui_vlm_nodes.
this is the structure, as same as you, it is 4.17 gb.
class AudioLDM2ModelPredictor:
def __init__(self):
from diffusers import AudioLDM2Pipeline
self.device = "cuda" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if self.device == "cuda" else torch.float32
# Use snapshot_download to manage the model download/cache
self.model_path = snapshot_download("cvssp/audioldm2",
local_dir=files_for_audio_model,
force_download=False, # Set to True to always download
local_files_only=False, # Download if not available locally
use_auth_token=False, # Set to True if using a private model
local_dir_use_symlinks="auto", # Auto-manage symlinks
ignore_patterns=["*.bin", "*.jpg", "*.png"]) # Ignore unrelated files
self.pipeline = AudioLDM2Pipeline.from_pretrained(self.model_path,
torch_dtype=torch_dtype).to(self.device)
self.generator = torch.Generator(self.device)
change above code with this inside custom_nodes/ComfyUI_VLM_nodes/nodes/audioldm2.py
class AudioLDM2ModelPredictor:
def __init__(self):
from diffusers import AudioLDM2Pipeline
self.device = "cuda" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if self.device == "cuda" else torch.float32
# Use snapshot_download to manage the model download/cache
self.model_path = files_for_audio_model
self.pipeline = AudioLDM2Pipeline.from_pretrained(self.model_path,
torch_dtype=torch_dtype).to(self.device)
self.generator = torch.Generator(self.device)
from comfyui_vlm_nodes.
Related Issues (20)
- Import "server" could not be resolved HOT 1
- MoonDream2 Error HOT 13
- MoonDream2 .gguf support
- Node is not generating new answers each time HOT 1
- I-quants incompatibility? HOT 2
- Cannot load model on Windows embedded python HOT 1
- Import failed HOT 1
- The VRAM usage is too high and cannot be released. HOT 1
- Can't install VLM nodes in ComfyUI HOT 14
- ChatMuscian Error HOT 1
- Suggestion: wave_form/sample_rate to vhs_audio
- GPU not utilized with standard llama-cpp-python HOT 1
- Error using xcomposer: Can't move a model that's been offloaded (delete this please)
- Get Keywords bug HOT 2
- Moondream error after installing VLM nodes HOT 2
- IMPORT FAILED in ComfyUI HOT 1
- Structured Output breaking. HOT 6
- LLaVA++ HOT 1
- ValueError("Prompt exceeds n_ctx") # TODO: Fix HOT 2
- RuntimeError: Failed to load shared library 'D:\AI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\llama_cpp\llama.dll
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 comfyui_vlm_nodes.