Instructions to use MonsterMMORPG/Wan_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MonsterMMORPG/Wan_GGUF with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MonsterMMORPG/Wan_GGUF", 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
Add ACEStep_1_5_XL_SFT_INT8_ConvRot (prequantized INT8 ConvRot ACE-Step 1.5 XL DiT)
1db8246 verified Download ACEStep_1_5_XL_SFT_INT8_ConvRot/config.json from MonsterMMORPG/Wan_GGUF: direct link, hf CLI and curl.
- Browser
- Download file 2.53 kB
-
https://huggingface.co/MonsterMMORPG/Wan_GGUF/resolve/main/ACEStep_1_5_XL_SFT_INT8_ConvRot/config.json
- Command line
-
hf download hf://MonsterMMORPG/Wan_GGUF/ACEStep_1_5_XL_SFT_INT8_ConvRot/config.json
-
curl -L -o config.json https://huggingface.co/MonsterMMORPG/Wan_GGUF/resolve/main/ACEStep_1_5_XL_SFT_INT8_ConvRot/config.json
2.53 kB
| { | |
| "architectures": [ | |
| "AceStepConditionGenerationModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_acestep_v15.AceStepConfig", | |
| "AutoModel": "modeling_acestep_v15_xl_base.AceStepConditionGenerationModel" | |
| }, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "audio_acoustic_hidden_dim": 64, | |
| "data_proportion": 0.5, | |
| "dtype": "bfloat16", | |
| "encoder_hidden_size": 2048, | |
| "encoder_intermediate_size": 6144, | |
| "encoder_num_attention_heads": 16, | |
| "encoder_num_key_value_heads": 8, | |
| "fsq_dim": 2048, | |
| "fsq_input_levels": [ | |
| 8, | |
| 8, | |
| 8, | |
| 5, | |
| 5, | |
| 5 | |
| ], | |
| "fsq_input_num_quantizers": 1, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "in_channels": 192, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9728, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "model_type": "acestep", | |
| "model_version": "base", | |
| "num_attention_heads": 32, | |
| "num_attention_pooler_hidden_layers": 2, | |
| "num_audio_decoder_hidden_layers": 24, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "num_lyric_encoder_hidden_layers": 8, | |
| "num_timbre_encoder_hidden_layers": 4, | |
| "patch_size": 2, | |
| "pool_window_size": 5, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": 128, | |
| "text_hidden_dim": 1024, | |
| "timbre_fix_frame": 750, | |
| "timbre_hidden_dim": 64, | |
| "timestep_mu": -0.4, | |
| "timestep_sigma": 1.0, | |
| "transformers_version": "4.57.0", | |
| "use_cache": true, | |
| "use_sliding_window": true, | |
| "vocab_size": 64003, | |
| "is_turbo": false, | |
| "lyric_alignment_layers_config": { | |
| "3": [ | |
| 18, | |
| 27 | |
| ], | |
| "4": [ | |
| 22 | |
| ], | |
| "5": [ | |
| 5, | |
| 6, | |
| 7 | |
| ], | |
| "6": [ | |
| 2, | |
| 12, | |
| 13 | |
| ], | |
| "7": [ | |
| 20, | |
| 21 | |
| ] | |
| } | |
| } |