Instructions to use AbstractPhil/geolip-beatrix-sana with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Sana
How to use AbstractPhil/geolip-beatrix-sana with Sana:
# Load the model and infer image from text import torch from app.sana_pipeline import SanaPipeline from torchvision.utils import save_image sana = SanaPipeline("configs/sana_config/1024ms/Sana_1600M_img1024.yaml") sana.from_pretrained("hf://AbstractPhil/geolip-beatrix-sana") image = sana( prompt='a cyberpunk cat with a neon sign that says "Sana"', height=1024, width=1024, guidance_scale=5.0, pag_guidance_scale=2.0, num_inference_steps=18, ) - Diffusers
How to use AbstractPhil/geolip-beatrix-sana with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Efficient-Large-Model/Sana_600M_512px_diffusers", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("AbstractPhil/geolip-beatrix-sana") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Download experiments/e003_trainer_parity/meta.json from AbstractPhil/geolip-beatrix-sana: direct link, hf CLI and curl.
- Browser
- Download file 842 Bytes
-
https://huggingface.co/AbstractPhil/geolip-beatrix-sana/resolve/main/experiments/e003_trainer_parity/meta.json
- Command line
-
hf download hf://AbstractPhil/geolip-beatrix-sana/experiments/e003_trainer_parity/meta.json
-
curl -L -o meta.json https://huggingface.co/AbstractPhil/geolip-beatrix-sana/resolve/main/experiments/e003_trainer_parity/meta.json
842 Bytes
| { | |
| "id": "e003_trainer_parity", | |
| "title": "Sana in the trainer: the diffusion-pipe adapter against the diffusers pipeline", | |
| "date": "2026-10-03", | |
| "kind": "test", | |
| "status": "done", | |
| "summary": "PASS: text conditioning identical, the transformer identical up to ordinary float rounding, and one image through the trainer's preview sampler within 0.32 brightness levels of the stock pipeline on average", | |
| "results": { | |
| "gate1": { | |
| "text_max_abs_diff": 0, | |
| "transformer_rel_error_vs_fp64": 1.45e-06, | |
| "stock_rel_error_vs_fp64": 9.9e-07, | |
| "ratio": 1.46, | |
| "bar": 2, | |
| "target_rel": 4.77e-07 | |
| }, | |
| "gate2": { | |
| "text": 0, | |
| "timesteps": 0, | |
| "latents_rel": 2.58e-05, | |
| "envelope_rel": 0.0178, | |
| "pixels_mean_levels": 0.32, | |
| "pixels_max_levels": 14, | |
| "stock_fp16_vs_fp32_mean": 0.66, | |
| "stock_fp16_vs_fp32_max": 65 | |
| } | |
| } | |
| } |