FLUX IMAGE TO IMAGE COMPOSITE WORKFLOW
flux schnell image to image workflow, which allows you to make commercial use of the images you create with it.
This workflow is mostly automatic, and is based on 2 images you upload, one image for the figure or object and another image for the background, the connection of these images, created automatically, is used as a reference for the final image.
In many cases it really felt like I was working with control net and ip adapter together.
It's a workflow that looks relatively simple, but it allows for very interesting combinations and changes, including the combination of text.
the version flux schnell , is openly available under an Apache2.0 license
#comfyui #flux #blackforestlabs #img2img #aiphotography #florence
follow me @ https://www.instagram.com/pixeleasel/
Previous video explaining Florence captioning
https://youtu.be/VAbQANZ3nak
Flux image 2 image composite workflow
https://drive.google.com/file/d/1q_LaXI9YB_l2dkQfWZKzT7zRp7HbSDQr/view?usp=sharing
florence 2 repo
https://github.com/kijai/ComfyUI-Florence2
flux text encoder (t5xxl + clip l )
https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main
flux schnell model + vae
https://huggingface.co/black-forest-labs/FLUX.1-schnell/tree/main
black forest labs
https://blackforestlabs.ai/announcing-black-forest-labs/
ComfyUI flux example
https://comfyanonymous.github.io/ComfyUI_examples/flux/