Instructions to use black-forest-labs/FLUX.1-Depth-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use black-forest-labs/FLUX.1-Depth-dev with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-Depth-dev", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Diffusion Single File
How to use black-forest-labs/FLUX.1-Depth-dev with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Error: ValueError: Trying to set a tensor of shape torch.Size([64]) in "bias" (which has shape torch.Size([128])), this looks incorrect.
Sorry for the easy question. I'm new to this and trying to see what I am doing wrong.
- The instructions says :
...
from diffusers import FluxControlPipeline, FluxTransformer2DModel
...
Is it supposed to be "FluxControlNetPipeline" instead of "FluxControlPipeline"?
I was getting this error until I changed it.
ImportError: cannot import name 'FluxControlPipeline' from 'diffusers'
- After I get everything to work I get this error
Error: ValueError: Trying to set a tensor of shape torch.Size([64]) in "bias" (which has shape torch.Size([128])), this looks incorrect.
Any suggestions on how I can resolve my error?
pip install diffusers==0.32.1
flux control model in_channels not equal to out_channels
self.out_channels = out_channels or in_channels
https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_flux.py#L261