Comments (5)
I can confirm that using attn injection is going to yield worse results. The reason behind is that IPAdapter also injects attn blocks, so there might be conflict on attn weights trying to adapt to 2 tasks at the same time.
from comfyui-layerdiffuse.
Tested that it works for IP-Adapter. Just make sure your input to IPAdapter should ideally have simple background or transparent background so that there are not too much noise information from the background getting captured.
from comfyui-layerdiffuse.
Got it. Thank you!
from comfyui-layerdiffuse.
Actually, just to follow your example, has the attention injection ever work for you? If I choose to use attention injection, the rendering seems broken to me, which is very different than the author mentioned here:
https://github.com/layerdiffusion/sd-forge-layerdiffuse
However, in practice, I find the layer_xl_transparent_attn.safetensors will lead to better results. This layer_xl_transparent_conv.safetensors is still included for some special use cases that needs special prompt understanding. Also, this model may introduce a strong style influence to the base model.
from comfyui-layerdiffuse.
It does seem like using Conv will impact the rendering quality. I'm wondering if there's any better solution to this.
from comfyui-layerdiffuse.
Related Issues (20)
- LayeredDiffusionCondJointApply error HOT 1
- Error occurred when executing LayeredDiffusionCondApply HOT 4
- [Bug]: Using the latest diffusers 0.27.2, your plugin will cause a lot of deprecation warnings. HOT 1
- Can generate no problem first que prompt, but after que again, it will have error HOT 3
- [Bug]: Fail to import node after comfyui update HOT 2
- [Bug]: The Picture Generated through foreground_to_blend is blur and dark
- bug
- Is there a tutorial for how to use the layerdiffuse json file in python? HOT 1
- [Bug]: !!! Exception during processing!!! 1024
- Please modify the deprecated API to the recommended version
- How can I use layer diffusion with pose controlnet?
- [Bug]: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! HOT 1
- Can I use my fine-tuned SDXL model with generating imgs from text prompts with transparent backgrounds using layerdiffuse? HOT 1
- [Bug]: Conflict with for_testing/attention_experiments
- No module named 'diffusers.models.unet_2d_blocks' HOT 1
- "Excuse me, what did I do wrong? I don't want this picture.
- [2024-3-9] Generate BG+Blended Given FG" workflow cannot run properly HOT 1
- No module named 'diffusers.models.unet_2d_blocks' Successfully installed diffusers-0.29.0
- When used with the ipadapter, the image cannot be extracted
- LayerDiffusion LayeredDiffusionDecodeRGBA error
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-layerdiffuse.