What is PanGu Draw SDXL V3？
“PanGu-Draw” is a novel latent diffusion model for text-to-image synthesis that adeptly accommodates multiple control signals: a diffusion-based generative model trained by HUAWEI.(learn more)
User Guide
This model and its running program are licensed under Apache 2.0. Please use this model and program in compliance with the license.
This model consists of two sub-models, one is the high_timestep model and the other is the low_timestep model. The running program needs to use both models simultaneously.
The running program of this model is still under development. It can only implement the text-to-image function for now. Please wait for further development if you need more functions.
This model has 5B parameters, and the running program is poorly optimized. Please make sure you have at least 20G of VRAM to run this program.
Comfyui and webui do not support this model，So I created a comfyui node to run this model(here)
PanGu Draw 3.0 PanGu Draw 3.0 models implemented with MindSpore.I migrated it from MindSpore to Torch and implemented it to run on ComfyUI.
Features
In contrast to version 2.0, Pangu Draw 3.0 has been subject to experimentation and updates across various aspects, including multi-language support, diverse resolutions, improved image quality, and model scaling. This includes:
The current industry's largest 5-billion-parameter Chinese text-to-image model.
Supports bilingual input in both Chinese and English.
Supports output of native 1K resolution images.
Outputs images in multiple size ratios.
Quantifiable stylized adjustments: cartoon, aesthetic, photography controller.
Based on Ascend+MindSpore for large-scale training and inference, using a self-developed MindSpore platform and Ascend 910 hardware.
Utilizes self-developed RLAIF to enhance image quality and artistic expression.
Author's Note:
This comfyui plugin is a program that I developed as a side project while learning stable diffusion. I am not a professional, and the program may have bugs. I apologize for my lack of technical skills.Description
FAQ
Comments (13)
can you describe what is this
@www913363043337 That is a nonsense explanation, and this looks like a fake model. I have reported it to the admins.
@MysteryWrecked I am writing some nodes to enable them to run on comfyui, preparing a model that will only be uploaded after completion, and providing an introduction after completion
@www913363043337 Still nonsense and still fake, but I guess the admins are good with it.
@MysteryWrecked Yes, of course my model is fake. I just made it up in five minutes. You are so clever to figure it out.
@www913363043337 Wow, you've become really good at English in the last few hours, edited your description and everything! Impressive!
遙遙領先
what is this?
As best I can tell from the explanation, this user is an amateur at SD trying to develop his own AI system, which sounds like a nonsense scam to me. These are supposed to be the base models for his new AI system, which isn't functional yet. This seems like a probable fake to me, but if you want to risk this Chinese data on your computer, let us know if it does anything.
忽悠到国外来了
Never mind what he says, those who have enough content and are willing to open source it should be supported. As for it trying to communicate values with this? Don't be ridiculous, are you still a minor? So easily influenced.
别管他怎么说，有足够内容，又肯开源的，都该支持。至于它想靠这传达价值观？别搞笑了，你还是未成年人吗？那么容易被影响。
打着官方的名号？
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.