Instructions to use hf-internal-testing/tiny-krea2-modular-pipe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hf-internal-testing/tiny-krea2-modular-pipe with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("hf-internal-testing/tiny-krea2-modular-pipe", 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
| { | |
| "_class_name": "Krea2Transformer2DModel", | |
| "_diffusers_version": "0.39.0.dev0", | |
| "attention_head_dim": 8, | |
| "axes_dims_rope": [ | |
| 4, | |
| 2, | |
| 2 | |
| ], | |
| "in_channels": 16, | |
| "intermediate_size": 32, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 4, | |
| "num_key_value_heads": 2, | |
| "num_layers": 2, | |
| "num_layerwise_text_blocks": 1, | |
| "num_refiner_text_blocks": 1, | |
| "num_text_layers": 12, | |
| "rope_theta": 1000.0, | |
| "text_hidden_dim": 16, | |
| "text_intermediate_size": 16, | |
| "text_num_attention_heads": 2, | |
| "text_num_key_value_heads": 1, | |
| "timestep_embed_dim": 8 | |
| } | |