Instructions to use 43ntropy/NEvo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use 43ntropy/NEvo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("43ntropy/NEvo", 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
| { | |
| "encoder_model_id": "epfl-neuroai/vjepa2-encoder-basic", | |
| "encoder_call": "predict_fmri", | |
| "text_to_image_model_id": "stabilityai/sdxl-turbo", | |
| "image_to_video_model_id": "Lightricks/LTX-Video-0.9.8-13B-distilled", | |
| "default_objective": "indices_mean", | |
| "default_device": "cuda", | |
| "default_mutation_rate": 0.25, | |
| "default_elite_frac": 0.35, | |
| "default_score_transform": { | |
| "enabled": false, | |
| "crop_scale": 0.8, | |
| "gaussian_sigma": 0.1, | |
| "num_draws": 4, | |
| "aggregate": "mean", | |
| "seed": 0 | |
| }, | |
| "default_score_frames": 24, | |
| "default_image_batch_size": 16, | |
| "default_video_batch_size": 8, | |
| "default_population_size": 20, | |
| "default_image_kwargs": { | |
| "num_inference_steps": 1, | |
| "guidance_scale": 0.0, | |
| "height": 512, | |
| "width": 512 | |
| }, | |
| "default_video_kwargs": { | |
| "num_inference_steps": 8, | |
| "num_frames": 25, | |
| "height": 512, | |
| "width": 512 | |
| }, | |
| "default_image_max_evals": 400, | |
| "default_video_max_evals": 200, | |
| "default_score_size": 224 | |
| } | |