Comments (7)
FYI metadata show on these sites also
https://jimpl.com/
https://exif.tools/
https://www.metadata2go.com/
from fooocus-mre.
@That-Dude Well @lllyasviel was kinda clear about his design choices for Fooocus:
Learned from Stable Diffusion, the software is offline, open source, and free. Learned from Midjourney, the manual tweaking is not needed, and users only need to focus on the prompts and images.
and to be honest those are pretty good assumptions - I respect and like those. I also like the idea of integrated sampler he implemented. But we have to remember that Fooocus isn't (and won't be) direct competition for A1111 or ComfyUI, where users need to get knowledge about SD pipeline details to use them. It's about delivering simple tool with clean UI, able to efficiently generate high quality output. It's about allowing users to focus on prompting, and letting the tool to do the rest (as much as reasonably possible).
I maintain this fork mainly for my own use, cause I have some experience with prompting, and I know that tweaking some parameters like steps, CFG, or CLIP skip is often best and fastest way to refine given prompt into image into what you want - changing CFG and/or CLIP Skip values allows you to control generalisation, for that example (and optimal values might vary per model + seed + prompt combination, or even per your own personal artistic taste). But as an old geek and experienced prompter I am not really target group of Fooocus, so I just accepted it - and hence this fork. If anyone else finds it useful / helpful - that's not my primary goal, but it's nice to hear :).
I intend to stick to the same design rules that are behind vanilla Fooocus, but I want to look at them from a bit more experienced prompter perspective. Let's say vanilla Fooocus is designed for 10yo users, A1111 and ComfyUI are for adults, and my fork could be good choice for teenagers - allowing you to have a bit more control (via Advanced settings) in case you want it, but also remaining clean and simple by default.
I agree with the philosophy of a simple interface design that just works, its what's needed to popularise SDXL. Having extra features in the advanced tab is a great design choice.
Your fork is what i would summarise as quality of life improvements for power users.
When A1111 gets its act together with SDXL I'll probably move over to that so i can access controlnet etc. But right now your fork is easily the best bet for creatives like me.
from fooocus-mre.
Good idea - I will look into it, but it might be a bit more complicated than simply changing key value from "prompt" to "comment" - I will test it with XnView. Properly implemented it should probably appear under "Image / Embedded Comment" (not "Extra / prompt" or "Extra / comment") in XnView, as in IPTC samples.
UPDATE: seems to be working in XnView with "Comment" key :).
from fooocus-mre.
@That-Dude fixed in 207712b6cad7601b311fb1e9e8de96622c94f08d - please check it out, and close if working as intended (I tested on XnView).
from fooocus-mre.
@That-Dude fixed in 207712b6cad7601b311fb1e9e8de96622c94f08d - please check it out, and close if working as intended (I tested on XnView).
Works great, thank you.
It looks like your fork is going to become popular as they have closed off the request in favour of their own proprietary solution. I'm genuinely baffled by this 🤷🏼♂️
from fooocus-mre.
@That-Dude Well @lllyasviel was kinda clear about his design choices for Fooocus:
Learned from Stable Diffusion, the software is offline, open source, and free.
Learned from Midjourney, the manual tweaking is not needed, and users only need to focus on the prompts and images.
and to be honest those are pretty good assumptions - I respect and like those. I also like the idea of integrated sampler he implemented. But we have to remember that Fooocus isn't (and won't be) direct competition for A1111 or ComfyUI, where users need to get knowledge about SD pipeline details to use them. It's about delivering simple tool with clean UI, able to efficiently generate high quality output. It's about allowing users to focus on prompting, and letting the tool to do the rest (as much as reasonably possible).
I maintain this fork mainly for my own use, cause I have some experience with prompting, and I know that tweaking some parameters like steps, CFG, or CLIP skip is often best and fastest way to refine given prompt into image into what you want - changing CFG and/or CLIP Skip values allows you to control generalisation, for that example (and optimal values might vary per model + seed + prompt combination, or even per your own personal artistic taste). But as an old geek and experienced prompter I am not really target group of Fooocus, so I just accepted it - and hence this fork. If anyone else finds it useful / helpful - that's not my primary goal, but it's nice to hear :).
I intend to stick to the same design rules that are behind vanilla Fooocus, but I want to look at them from a bit more experienced prompter perspective. Let's say vanilla Fooocus is designed for 10yo users, A1111 and ComfyUI are for adults, and my fork could be good choice for teenagers - allowing you to have a bit more control (via Advanced settings) in case you want it, but also remaining clean and simple by default.
from fooocus-mre.
Issues solved - closing it.
from fooocus-mre.
Related Issues (20)
- JugernautXL not recognized HOT 2
- I get an error when I launch the tool - 'Lora file not found!' HOT 2
- Generates without any problem first time, then runs out of ram.
- The installation of V2.0.78.5 failed many times and the following error message appeared. What is the reason? HOT 1
- weird preview generating problem here and in the main repo
- My boss, MRE version 2.1 ready? HOT 12
- load_settings, e: 'utf-8' codec can't decode byte 0xd7 in position 1206: invalid continuation byte HOT 1
- Extreme RAM usage on colab
- fooocus-MRE loads model on every startup HOT 1
- All of a sudden
- How to use SDXL CHECKPOINTS that are in subfolders?
- [FIXed] Colab Error WARNING[XFORMERS] HOT 1
- running an error message
- Error while deserializing header: HeaderTooSmall
- ERROR: Failed building wheel for pygit2sudo
- paths.json not recognized
- Colab Error – xFormers wasn't build with CUDA support
- Ordering of Models and Loras
- Running different models similar to running different styles
- complaints
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 fooocus-mre.