Text-to-Video
Diffusers
Safetensors
English
efficient
mobile video generation
dit
pyramidal diffusion
Instructions to use karnewar/Neodragon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use karnewar/Neodragon with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("karnewar/Neodragon", 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": "PyramidDiffusionMMDiT", | |
| "_diffusers_version": "0.34.0.dev0", | |
| "add_temp_pos_embed": true, | |
| "attention_head_dim": 64, | |
| "caption_projection_dim": 1536, | |
| "gradient_checkpointing_ratio": 0.6, | |
| "in_channels": 16, | |
| "interp_condition_pos": true, | |
| "joint_attention_dim": 4096, | |
| "max_num_frames": 200, | |
| "num_attention_heads": 24, | |
| "num_layers": 18, | |
| "patch_size": 2, | |
| "pooled_projection_dim": 2048, | |
| "pos_embed_max_size": 192, | |
| "pos_embed_type": "sincos", | |
| "qk_norm": "rms_norm", | |
| "sample_size": 128, | |
| "temp_pos_embed_type": "rope", | |
| "use_gradient_checkpointing": false, | |
| "use_t5_mask": true, | |
| "use_temporal_causal": true | |
| } | |