Instructions to use chenzeyang1/T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use chenzeyang1/T with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("chenzeyang1/T", torch_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
| CONTROLLER_HEART_BEAT_EXPIRATION = 30 | |
| WORKER_HEART_BEAT_INTERVAL = 15 | |
| LOGDIR = "." | |
| # Model Constants | |
| IGNORE_INDEX = -100 | |
| IMAGE_TOKEN_INDEX = -200 | |
| DEFAULT_IMAGE_TOKEN = "<image>" | |
| DEFAULT_IMAGE_PATCH_TOKEN = "<im_patch>" | |
| DEFAULT_IM_START_TOKEN = "<im_start>" | |
| DEFAULT_IM_END_TOKEN = "<im_end>" | |
| IMAGE_PLACEHOLDER = "<image-placeholder>" | |
| # IMG tokens for VLM-guided diffusion (16 tokens for edit conditioning) | |
| IMG_TOKENS = [f"[IMG{i}]" for i in range(16)] | |