(WIP)

This is a finetune of FLUX.1-dev. This model aims to generate multiple views of an object given a single view.

The dataset was curated by re-rendering and cleaning up the Objaverse dataset. Example image from the dataset: Dataset Example Image

I tried multiple training runs with different hyperparameters, and It seems that the model just learns the output structure at a very high level, but doesn't learn the details. Here are some example outputs when asked to generate multiple views of a bird Bird Multiple views 1 Bird Multiple views 2

Loss graphs for two best training runs Loss

Misc Details

The training method here is similar to FLUX Depth Control, and FLUX Canny Control. The conditioning image is added as extra channels in the input, and the model is asked to denoise the noisy channels.

Thanks to Modal for sponsoring the compute for this.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for thesantatitan/flux-control-orbit

Finetuned
(354)
this model

Dataset used to train thesantatitan/flux-control-orbit