TBNilles/ComfyUI-Manager
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update DB

Browse Source
This commit is contained in:
Dr.Lt.Data
2024-06-03 22:16:03 +09:00
parent c098e2fe50
commit 8fde03db1e
6 changed files with 113 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
custom-node-list.json
View File

@@ -8130,7 +8130,7 @@
{
"author": "AIFSH",
"title": "ComfyUI_V-Express",
"id": "v-express",
"id": "v-express-aifsh",
"reference": "https://github.com/AIFSH/ComfyUI_V-Express",
"files": [
"https://github.com/AIFSH/ComfyUI_V-Express"
@@ -9846,6 +9846,28 @@
"install_type": "git-clone",
"description": "Nodes:commonly_node."
},
{
"author": "tiankuan93",
"title": "V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation",
"id": "v-express",
"reference": "https://github.com/tiankuan93/ComfyUI-V-Express",
"files": [
"https://github.com/tiankuan93/ComfyUI-V-Express"
],
"install_type": "git-clone",
"description": "[Original] In the field of portrait video generation, the use of single images to generate portrait videos has become increasingly prevalent. A common approach involves leveraging generative models to enhance adapters for controlled generation. However, control signals can vary in strength, including text, audio, image reference, pose, depth map, etc. Among these, weaker conditions often struggle to be effective due to interference from stronger conditions, posing a challenge in balancing these conditions. In our work on portrait video generation, we identified audio signals as particularly weak, often overshadowed by stronger signals such as pose and original image. However, direct training with weak signals often leads to difficulties in convergence. To address this, we propose V-Express, a simple method that balances different control signals through a series of progressive drop operations. Our method gradually enables effective control by weak conditions, thereby achieving generation capabilities that simultaneously take into account pose, input image, and audio.\nNOTE: You need to downdload [a/model_ckpts](https://huggingface.co/tk93/V-Express/tree/main) manually."
},
{
"author": "CMonk",
"title": "Stable Projectorz Bridge",
"id": "projectorz",
"reference": "https://github.com/tianlang0704/ComfyUI-StableProjectorzBridge",
"files": [
"https://github.com/tianlang0704/ComfyUI-StableProjectorzBridge"
],
"install_type": "git-clone",
"description": "This custom nodes enables Stable Projectorz to work with ComfyUI Directly."
},
@@ -10244,16 +10266,6 @@
],
"install_type": "unzip",
"description": "This is a node to convert an image into a CMYK Halftone dot image."
},
{
"author": "CMonk",
"title": "Stable Projectorz Bridge",
"reference": "https://github.com/tianlang0704/ComfyUI-StableProjectorzBridge",
"files": [
"https://github.com/tianlang0704/ComfyUI-StableProjectorzBridge"
],
"install_type": "git-clone",
"description": "This custom nodes enables Stable Projectorz to work with ComfyUI Directly."
}
]
}