Instructions to use SJTU-DENG-Lab/Think-Then-Generate-T2I with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SJTU-DENG-Lab/Think-Then-Generate-T2I with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SJTU-DENG-Lab/Think-Then-Generate-T2I", 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 Settings
- Draw Things
- DiffusionBee
Commit History
-
Add model card for Think-Then-Generate
Verified signatureHi! I'm Niels from the Hugging Face community team. I've opened this PR to add a comprehensive model card for the Think-Then-Generate model. This includes: - Relevant metadata (`pipeline_tag`, `library_name`) for improved discoverability. - Direct links to the paper, GitHub repository, project page, and Hugging Face Space. - A summary of the 'Think-Then-Generate' paradigm and its methodology. - The official installation instructions and sample inference command from the GitHub repository. - The BibTeX citation. Please let me know if any adjustments are needed. Thanks!a13a195
-
Upload folder using huggingface_hub
Verified signature7fbbdec -
initial commit
Verified signature6aa96b2