Flux.2 Klein Mix Workflow
Workflow with main focus on Image Editing, with control over Image Sizes. Trying to only use the more common Custom Nodes or ones that do not have requirements for a easy and safe installation.
Aiming for consistency and support edits for up to 4 images and Text to Image, 3 different Controlnets, different Inpainting methods and Outpainting. Nodes for selecting image sizes and Aspect Ratio. Uses Flux2 Klein Enhancer nodes, for consistency and prompt impact. Color matching and different sampler with ETA setting.
The workflow has many notes that explain things inside, which you can read or delete.
There is a second Version inside for people that use Lora Manager so you can pick what you want.
The workflow only support a Positive Prompt except for the 2-pass mode in V5 for T2I that uses both the Base and the Normal model and a negative prompt.
All custom nodes used:
Essentials
Rgthree
Easy-Use
Impact Pack
KjNodes
GGUF
Controlnet_aux
LayerStyle
ArtVenture
Below Does not have any requirements making for an easier and safer install:
Inpaint-CropAndStitch
ModdedNodes
Comfyroll
ControlAltAI
Flux2Klein-Enhancer
CRZnodes
mxToolkit
ZImageTurbo-FlowSampler
Note that V2 and V1 do not use the same custom nodes, and are harder to use because of that, and I do not recommend using them!
Feel free to criticize, comment or ask questions.
Description
Added a new 2-pass mode for T2I that uses both Base and the Normal models.
Added support for the new versions of the Enhancer nodes.
FAQ
Comments (8)
Guys, if the workflows do not run, I noticed a problem with custom_nodes\comfyui-art-venture ! try a manual download (git clone and install requirement). If it still not working try sipherxyz version on github.
Image generation is being prevented because, for some reason, the "ImageOutput" of "Z-Image Turbo Sampler" is connected to the sampler within "Generation Settings".
Is this a mistake by the author? Or is there something wrong with my environment?
Not a mistake, it works for Flux.2 Klein also and has a sampler and options that I wanted to add that give imo a little better results.
So no that is not the error. When you have not given a error message from the Console / log I can not say what is wrong but probably some custom node you do not have installed?
I figured it out myself. It turns out that installing “tpc2233/ComfyUI-Z-Image-Turbo” had caused “Z-Image Flow Sampler” to be converted into something else. Sorry for the fuss.
Tested V5 and can't get it working. It generates three black images within a second. No error output. Using GGUF.
The previews should be black if you have not set a mode to use them. But the compare and save image you should always see. Have you looked in the console there should be something there why it is not working. But if you are sure you are using the correct model and have set the workflow to use GGUF it is probably some custom node you are missing, some some conflict with a custom node. You can write 'pip check' in a console window to check for broken requirements. If you are using portable version you need to be inside the virtual environment first though. Or the manager inside Comfyui can sometimes also see those things.
I am not able to generate image. got prompt
Failed to validate prompt for output 1203:
* DF_Divide 2710:2685:
- Exception when validating inner node: list index out of range
* DF_Multiply 2710:2700:
- Exception when validating inner node: list index out of range
Output will be ignored
invalid prompt: {'type': 'prompt_outputs_failed_validation', 'message': 'Prompt outputs failed validation', 'details': '', 'extra_info': {}}
My guess is that you have some custom node that is not updated. Or there is some conflict. I personally run portable Comyui and have several different ones as adding too many custom nodes usually breaks stuff. If updates broke it I can make a new version but do not have time currently. Will check it later.