Cavendish

Cairlup!

Thank you!

👍

Nothing here is real, it's just the fever dream of my GPU. I'm not even using a base photo as a controlnet guide. It's 100% text-to-image.

Agreed. Still looking for the right mix of anatomy finetuning models.

Not using a small model, this is the full 22 gigabyte Flux.1 Dev fp32, plus a couple of customized lora merges that I'm experimenting with. I have a 3090 with 24GB VRAM, which gets maxed out. Takes about 1:30 to 2:10 to generate each image at 2 megapixel resolutions. It's a real basic flux workflow in Comfy, I don't even run them through any upscaling nodes.

Kind of frightening how fast things are improving, really. In another year, you won’t be able to trust any image you see.

gracias!

Thank you. I aim to please.

I'm using Flux.1 (dev). It's a huge step up from any of the Stable Diffusion 1.5 or SDXL models.

Just got the new 0.4.2 testflight version. That is a very long list of updates and fixes! Thanks for continuing to make improvements.

After a careful review, I believe you are correct. I'll take the matter up with the clothier.