Yet Another Workflow : easy t2i+edit

I've aimed at a user-friendly UI for ComfyUI. There's a balance between complexity and ease of use, and this workflow aims to give you useful controls with clear guidance on what you need to care about. I hope these will be helpful to anyone strugging with quality and the general UI-isms of ComfyUI. I've taken the time to color code and add lots of notes. Please read the notes, I've tried to make them useful!

This a the workflow I use, it's not aimed at a skill level. It's designed to be easy to use and adjust with some UI concessions and labeling to ensure you can pilot it with less experience in a way that is more sophisticated than the official example workflows, which can be easy to break.

The primary goal with this workflow is to give you a strong foundational place to generate generate text-to-image (T2I) outputs without having to fuss too much. Additionally, the workflow supports an edit LoRA for doing image revisions.

This is the first image workflow based on the same principles as my video workflows. Krea 2 is a fairly simple model. This workflow doesn't have any special tricks, it's just a good workflow that would allow you to pivot your experience using it to video and back as a kind of UX ecosystem.

The secondary goal here is to provide a consistent interface to interact with different samplers and now different models.

The green controls are the stuff you generally want to mess with.

Now for Krea 2

One of the strengths of respecting a consistency to a UI is that it allows you to change things under the hood to enable people to explore new techniques without changing the majority of their experience. Whether you're familiar with my Wan 2.2 workflow, my LTX-2.3 workflow, my MiniMax H3 workflow, or whether this is your first experience with my workflows, once you're comfortable with one of them, the goal is that you can switch between them with minimal fuss.

Krea 2 is a siren call. I've spent a lot of time using GPT Image models. I love them, but they're gated. Krea 2 is the first open weights model I've used that can produce, my my sentiments, jaw dropping results. It's got pretty good prompt adherance, and it can do an incredible amount of things proficiently out of the box. It's capable of a huge number of styles, and LoRA's push it further over the edge. Combine it with a video tool like MiniMax H3, and we're really in a golden age of open weights models.

Any problems?

It does have some down sides: Using the Tubro LoRA for performance can cause results to become somewhat same-y. You'll notice this with a bunch of the available quantized checkpoints people have made. Because Krea is very literal in it's prompting, the model tends to be less "creative" than other models when accelerated, so varying your prompt can become more important to achieving variety. If you're using the raw model, you can try lowering the strength of the Turbo LoRA to give it a bit more freedom. (There are lot's of things to try!)

Like it?

Give it a like! Tag it as a Resource when you use it! Support on Patreon or a tip on Ko-fi are also welcome. Yellow Buzz will go towards promoting awareness here on Civit.

Need help?

I like helping people get going with this stuff, so if you want help message me. If you want extended one-on-one help, there's an option on the Patreon. I'm happy to walk you through the details, answer your questions, and give you some extra tips and tricks, and scripts. I've done this for a few folks, I'll save you money and headaches.

I've also written an article here on getting it going with my Runpod template. The template will vastly expedite and simplify getting things up and running.

General Advice

• Make lots of images! Post your images! Don't fuss with the tech! Be smart about how you spend your time with this stuff. A down side to images are that it's easy to make bajillion of them. Try different things. Try not to make too much work for yourself in sifting through the results.

• I use RunPod, but this will run locally. I use RTX 5090 or PRO 6000 or the H100 SXM. I'm often doing this in conjunction with video work, and performance is linear so 3.0 MP generations are very fast on higher end hardware. If you've not used RunPod before, sign up with my link; we'll both get some free credit. See the article for more.

• If you run this outside of Runpod, you'll need to install some custom nodes. To do that, click the "Manager" button at the top of the Comfy interface, and then click the "Install Missing Custom Nodes". Click "Install" on each one - I recommend in order; you'll need to wait till each has installed. Do not bother restarting ComfyUI until they are all installed. The RunPod template has them preinstalled.

• If the wires bother you, there's a button in the bottom right on the floating UI that will hide them.

• This workflow is setup for .safetensors models, but you can use GGUF if you want to make the changes node changes.

Costs?

Still benchmarking. Will add some data soon.

Troubleshooting

If a node is missing (bright thick red outline with a warning when you open the workflow), you can install them by going to Manager > Install Missing Custom Nodes, and pressing Install on any the nodes that show up there.

If a model is missing (bright thick red outline with a warning when you open the workflow), you'll need to download the missing model and place it in the correct directory in your ComfyUI folder. (ex: /ComfyUI/models/loras/).

If you are getting any errors related to a custom node, it's possible something has changed recently in the software. It might be useful to change a version back to the last "stable" build in these situations.