Update 26.11.24
This workflow eliminates the need for a face and skin detailer. The idea is to render directly at a significantly higher resolution and then correct any imperfections in the image using a simple ultimate upscaling process.
Additionally, image details are enhanced through the Detail Daemon and additional noise injection. In the initial samplers, the sigmas are split to allow the first steps to render with high guidance and the final steps with low guidance. This makes the images appear more natural and less AI-like.
This approach works very well but requires extremely powerful hardware and is not particularly fast. However, the resulting images are of exceptionally high quality.
Update 07.10.24
The workflow now supports GGUF models, improved ViT-L/14 CLIP, and has a significantly enhanced UltimateUpscaler thanks to the fill nodes.
Attention: The skin detailer with upscaler workflow is extremely hardware-intensive. On an RTX 3090, it takes about 10-12 minutes to generate a single image. If you want to generate images faster, please use the older workflow.
Flux is a 12 billion parameter model and it's simply amazing!!! Here’s a workflow from me that makes your face look even better, so you can create stunning portraits.
You can find the download links for the Flux model in the notes within the workflow.
Description
FAQ
Comments (20)
Great job, thanks for sharing!
where do i place the lut file?
great, and thank you, but what's with all the repeated credit boxes in the workflow wasting valuable space. DELETE DELETE DELETE.
this made creating high quality, fun images a breeze. Thanks a lot!
It gives me error on the DualCLIPLoder, I have:
clip name1 flux1-dev-fp8.safetensors
clip name2 clip_l.saferensors
type flux
What is the problem ? What clip model to I have to use ?
flux1-dev-fp8.safetensors doesn't sound like a clip model. you need Clip-L and T5-XXL. I think you're missing t5xxl_fp8_e4m3fn.safetensors. see here: https://education.civitai.com/quickstart-guide-to-flux-1/
Hallo Dennis, wieder mal eine sehr gute Arbeit. Die Geschwindigkeit ist sehr gut und die Ergebnisse sind wie gewohnt sehr sauber.
Beste Grüße Thorsten
Danke Thorsten :) Hab schon ein paar Ideen für Verbesserungen des Workflows. Bin aber erstmal in Urlaub und genieße die Sonne :)
Hello, thank you for the workflow.
Receiving error:
Error occurred when executing UNETLoader: 'conv_in.weight'
Did you update ComfyUI?
Hello.. what to do with this presetpro...cube file that comes with it?
it's a lut file for automated colorgrading
where do we get the lut files?
@denrakeiw Thank you!