Flux finetune that is trained on Glitches generated by a Processing Script, WIP.
This model costs approximately $0.091 to run on Replicate, or 10 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia H100 GPU hardware. Predictions typically complete within 60 seconds. The predict time for this model varies significantly based on the inputs.
Experimenting with Flux finetune on Glitch Images generated using a Processing script I had fun with recently. WIP and doesn’t enforce the style consistently but it’s pretty cool.
Plays well with andreasjansson/flux-shapes LoRA - also trained on synthetic data with a nice opinionated color palette. Check the examples for trigger words and weights
