Flux.1 IMG2IMG + Using LLMs for Prompt Enhancement in ComfyUI!

Nerdy Rodent
Nerdy Rodent
20,750
0
Published 2024-08-07
While we wait for the Flux.1 Dev controlnet models and ip adapters in ComfyUI, how about some composition control using image to image? Turns out that works just great, only often I find myself need longer prompts as they seem to generate better images. Or maybe if I could just ask for what I want, even if I’m not really sure? If only there was an AI to help with that?

Links, as shown in the video:
ComfyUI Flux workflows - comfyanonymous.github.io/ComfyUI_examples/flux/
LLM Party - github.com/heshengtao/comfyui_LLM_party
Ollama - github.com/ollama/ollama

Want to support the channel? Get pre-made workflows and more!
www.patreon.com/posts/ai-enhanced-flux-109665789

== Beginners Guides for ComfyUI ==
1. Installing Anaconda for MS Windows Beginners -    • Anaconda - Python Installation made E...  
2. Installing ComfyUI for Beginners -    • Installing ComfyUI for the First Time!  
3. ComfyUI Workflows for Beginners -    • ComfyUI Workflow Creation Essentials ...  
All Comments (21)
  • @memoryhero
    The constant quick side commenting was magical in this vid - you kept it brief enough so that veterans won't feel bogged down by old redundant info but also that newbies will highly benefit from it. World class tutorial protocol.
  • @esuvari
    Canny for flux has just been released today
  • @michaelbrandonfalk5316
    2:41 WHAAAAAT That's how that works! Oh my goodness! I heard someone say the picture is the workflow, but didn't get it. Now I do :) Thank you!
  • @Copperpot5
    Excellent job on this workflow! Playing w/ it now after making a few of my own/using some common on civ/discord, but your incorporation of the LLM Party node + autosizing/etc is simply brilliant. Hope all is well!
  • @synthoelectro
    and for those who are stuck with 4GB VRAM, just use a large virtual memory and about 768 x 768, it takes up to 8 mins depending but hey, we did it before on 1.5. and SDXL, we can keep going, you can do this.
  • @akratlapidus2390
    Nerdy, you always deliver!!! 👌🏻👏🏻👏🏻👏🏻👏🏻
  • @BirkB1
    Thank you. LLM party sounds awsome 😄
  • @Cadmeus
    A node that really helps to manage latent/image sizing btw is an underappreciated little extension from Ser-Hilary, called SDXL_sizing. Automatically spits out the right size for any base resolution (e.g. 512, 1024, 2048), at any given aspect ratio. I use wildcards from Impact Pack as an input to the aspect ratio setting, which works really well with Flux.
  • @scarletsword45
    I really like Flux, but I'm disappointed that I keep having to buy a new GPU to keep up with the demands of new AI art models. 😁
  • @jonmichaelgalindo
    Even if outputs were non-commercial, education and reporting are protected fair use. (Education and reporting are inherently commercial. Teachers and journos have to get paid.) Fair use is the doctrine all AI model training is built on. 😊
  • @Pygon2
    Regarding the license, while the Output can be "used for commercial use", Flux has pretty clearly been trained on copyrighted material. While Flux (like other AI companies) might be able to get the fair use exceptions for the training that is currently being litigate across a number of cases, you would still likely be personally liable for every copyright infringement in the output. Those damages can be significant, so something just to keep in mind if your intention is to use the outputs commercially.
  • @vitalis
    I see rodent I click. Simple 👍
  • @equilibrium964
    A face detailer workflow for flux would be really useful.