Instructions to use Guoyanjun/MemorizeWhenNeed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Guoyanjun/MemorizeWhenNeed with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Guoyanjun/MemorizeWhenNeed", 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
| { | |
| "_class_name": "WanControlnet", | |
| "_diffusers_version": "0.37.0.dev0", | |
| "added_kv_proj_dim": null, | |
| "attention_head_dim": 128, | |
| "cross_attn_norm": true, | |
| "downscale_coef": 8, | |
| "eps": 1e-06, | |
| "ffn_dim": 8960, | |
| "freq_dim": 256, | |
| "hidden_channels": 36, | |
| "in_channels": 6, | |
| "num_attention_heads": 16, | |
| "num_layers": 8, | |
| "out_proj_dim": 5120, | |
| "patch_size": [ | |
| 1, | |
| 2, | |
| 2 | |
| ], | |
| "qk_norm": "rms_norm_across_heads", | |
| "rope_max_seq_len": 1024, | |
| "text_dim": 4096 | |
| } | |