Text-to-Image
Diffusers
English
controllable text-to-image generation
diffusion models
3D layout control
occlusion reasoning
Instructions to use va1bhavagrawa1/seethrough3d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use va1bhavagrawa1/seethrough3d with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("va1bhavagrawa1/seethrough3d", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Move metadata to YAML header and add paper links
#1
by nielsr HF Staff - opened
Hi! I'm Niels from the Hugging Face community team.
I noticed that the metadata for this model (such as the task, license, and library name) is currently inside a commented-out block in the README. This prevents the model from being correctly categorized and searchable on the Hub.
This PR moves the metadata into the YAML header and adds a link to the base model (FLUX.1-dev) and the training dataset. This will ensure the model shows up in the right categories and includes a "trained on" section.
va1bhavagrawa1 changed pull request status to merged