mirror of
https://github.com/runyanjake/jake.runyan.dev.git
synced 2025-10-04 05:47:30 -07:00
Add flux1 blog
This commit is contained in:
parent
e0355352f5
commit
e34dbad45a
BIN
website/blog/2024-08-16-flux-1/chat-gpt.png
Normal file
BIN
website/blog/2024-08-16-flux-1/chat-gpt.png
Normal file
Binary file not shown.
After Width: | Height: | Size: 29 KiB |
BIN
website/blog/2024-08-16-flux-1/comfy.png
Normal file
BIN
website/blog/2024-08-16-flux-1/comfy.png
Normal file
Binary file not shown.
After Width: | Height: | Size: 803 KiB |
BIN
website/blog/2024-08-16-flux-1/flux1.png
Normal file
BIN
website/blog/2024-08-16-flux-1/flux1.png
Normal file
Binary file not shown.
After Width: | Height: | Size: 1.0 MiB |
49
website/blog/2024-08-16-flux-1/index.mdx
Normal file
49
website/blog/2024-08-16-flux-1/index.mdx
Normal file
@ -0,0 +1,49 @@
|
||||
---
|
||||
slug: flux-1
|
||||
title: Image Generation with Flux.1
|
||||
authors: [jrunyan]
|
||||
tags: [ai, workflow]
|
||||
---
|
||||
|
||||
# Upgrading my Image Generation Pipeline
|
||||
|
||||
Stable diffusion and its peers have proven to be the beginning of the wide applications of image generation. Over the past year, AI-generated content has become a lot more prevalent on the internet, showing up everywhere from social media to content mill news sites.
|
||||
|
||||
In my last iteration of the [PWS Recipes site](https://recipes.whitney.rip), I used the recent release of SDXL in a ComfyUI pipeline to generate static content for the site.
|
||||
|
||||
Now, with the release of newer image generation model Flux, I go back for another stab at generating these images.
|
||||
|
||||
## Pipeline
|
||||
|
||||
Prompt generation is hard. Let's ironically use ChatGPT to generate a prompt for Flux.1.
|
||||
|
||||

|
||||
|
||||
The ComfyUI pipeline used is very simple. Just a single KSampler pass to generate the image.
|
||||
|
||||

|
||||
|
||||
And, we're done.
|
||||
|
||||
## Thoughts
|
||||
|
||||
So, obviously some things have improved since the last time I looked into this space, and others have not.
|
||||
|
||||
The most impressive leap forward has been in text generation, but that being said it's not always perfect:
|
||||
|
||||

|
||||
|
||||
In the past we had to do with specially trained models that typically generated text with a lot of errors, usually smashing together characters.
|
||||
The current state of text generation is far better, the text that is specified in the prompt is treated specially and is correct more than it is incorrect.
|
||||
Despite this, background text (anything that not generated as a result of explicitly asking for it in the prompt) frequently has some of the original issues we faced.
|
||||
|
||||

|
||||
|
||||
Overall, the steps are positive, and the release of new tools means we have new limits to push the boundaries of.
|
||||
|
||||
## Resources
|
||||
|
||||
[Flux.1](https://flux1.io/)
|
||||
|
||||
[ComfyUI](https://github.com/comfyanonymous/ComfyUI)
|
||||
|
BIN
website/blog/2024-08-16-flux-1/tobeeandmaymay.png
Normal file
BIN
website/blog/2024-08-16-flux-1/tobeeandmaymay.png
Normal file
Binary file not shown.
After Width: | Height: | Size: 1.1 MiB |
Loading…
x
Reference in New Issue
Block a user