flux

flux copied to clipboard

Improve flux-1-dev to create images to replicate styles of world-class movie characters and their franchises

2

Since ChatGPT launched its imagen image creator that stunned the world for creating ghibli-esque images, can't flux-1-dev do the same thing , but better, this time expanding its reach to...

gmanskibiditoilet

Training a model for a character

2

Is there a way in dev to train a model for an individual character. If yes, how?

Abimanikumaran

Will Redux in FLUX.1 Dev be Retrained Based on SigLIP 2? Will the Training Details of Redux Be Made Public?

1

suzhoushr

### Issue Description **Problem**: When executing `python -m flux.cli --prompt="A beautiful forest"`, the following error occurs: ```python Traceback (most recent call last): File "", line 198, in _run_module_as_main File "",...

Kitgooo

CUDA import Error while running `demo_gr.py`

1

## Description of Issue I am trying to perform Inference using the `Flux.1 Schnell` model by running `demo_gr.py`, but I am receiving a cuda import error, although `torch.cuda.is_available()` is returning...

usamashami11

Hi :wave: First of all, thank you for open-sourcing Flux! I am having issues installing `flux` using `pip` due to `ruff` being included in the mandatory dependencies with a fixed...

francois-rozet

How to erase an object by flux?

1

liguopeng0923

ValueError: Trying to set a tensor of shape torch.Size([3072, 64]) in "weight" (which has shape torch.Size([3072, 384])), this looks incorrect.

2

``` import torch from diffusers import FluxFillPipeline from diffusers.utils import load_image image = load_image("https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/cup.png") mask = load_image("https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/cup_mask.png") pipe = FluxFillPipeline.from_pretrained("black-forest-labs/FLUX.1-Fill-dev", torch_dtype=torch.bfloat16).to("cuda") image = pipe( prompt="a white paper cup", image=image, mask_image=mask,...

haozhuoyuan

I want to ask in GitHub when I use comfyUI to run the model, the model always runs in CPU; how could I change to GPU? VAE load device: cuda:0,...

vtchao

Currently, the inference optimization solution (TensorRT) takes a very long time to compile and the UX is not great, and it doesn't support LoRA. Compared to TensorRT, `torch.compile` has a...

yf225