Hello ♥
for whatever reason you want to show me appreciation, you can: ❤️Ko-Fi❤️
___________________
Please Check out Blackforestlabs
these guys are absolt amazing. Thank you so much for creating this stunning masterpiece ♥
Since there is no place yet where I upload my flux images here on Civit, here is the simple workflow to create FLUX images using text prompts.
You can use the fp8 or fp16 variant.
In the future I will extend this workflow. (upscaling, ...)
Please read the original documentation
https://huggingface.co/black-forest-labs/FLUX.1-dev
Please load the workflow and
in the notes, you will find all links to download the models and the right path.
You can use this as help too
https://comfyanonymous.github.io/ComfyUI_examples/flux/
Settings for FP8
Settings for FP 16
Hope you get a lot of beautiful results ♥
Description
now you get 5 diffrent images out of one prompt
FAQ
Comments (10)
Thank you for this workflow! Once again fantastic work from you :)
I just started experimenting with flux yesterday, It's pretty cool
👍😊
Hope you get a lot of great results! ❤️
@AIDigitalMediaAgency I have a few up in my gallery right now, wait I will post a few here, I basically have the same workflow anyway, except for your text enhancer node
@AIDigitalMediaAgency Today I want to try out your logomaker to turn my logo in to a cool gif, the ST2 one
@serget2 awesome results, thank you for the images ♥
Download Model: flux1-dev-fp8.safetensors 11.9GB (if you machine not power enough, try this one)
https://huggingface.co/Kijai/flux-fp8/tree/mainTo: ComfyUI/models/unet/
Download CLIP:t5xxl_fp8_e4m3fn.safetensors: 4.89 GB (less than 32GB ram use fp8)
clip_l.safetensors: 246 MB
https://huggingface.co/comfy.../flux_text_encoders/tree/main
To: ComfyUI/models/clip/
Download VAE:ae.sft: 335 MB
ae.sft · black-forest-labs/FLUX.1-schnell at main (huggingface.co)
To: ComfyUI/models/vae/
links are not working it gives 404
Link for unet model: t5xxl_fp8_e4m3fn.safetensors · comfyanonymous/flux_text_encoders at main (huggingface.co)
Link for clip model: clip_l.safetensors · comfyanonymous/flux_text_encoders at main (huggingface.co)
The VAE link worked for me.
Thanks