Instructions to use fal/Marigold-v2-Qwen-VAE-FlashPack with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fal/Marigold-v2-Qwen-VAE-FlashPack with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fal/Marigold-v2-Qwen-VAE-FlashPack", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Download flashpack_conversion.json from fal/Marigold-v2-Qwen-VAE-FlashPack: direct link, hf CLI and curl.
- Browser
- Download file 631 Bytes
-
https://huggingface.co/fal/Marigold-v2-Qwen-VAE-FlashPack/resolve/main/flashpack_conversion.json
- Command line
-
hf download hf://fal/Marigold-v2-Qwen-VAE-FlashPack/flashpack_conversion.json
-
curl -L -o flashpack_conversion.json https://huggingface.co/fal/Marigold-v2-Qwen-VAE-FlashPack/resolve/main/flashpack_conversion.json
631 Bytes
| { | |
| "epoch": 6, | |
| "source_repo": "Qwen/Qwen-Image-Edit-2509", | |
| "source_revision": "d3968ef930e841f4c73640fb8afa3b306a78167e", | |
| "dtype": "bfloat16", | |
| "components": [ | |
| "vae" | |
| ], | |
| "components_only": null, | |
| "variant": null, | |
| "include_root": false, | |
| "ignore_names": [], | |
| "ignore_prefixes": [], | |
| "ignore_suffixes": [], | |
| "files": null, | |
| "pack_files": null, | |
| "pickle_key": null, | |
| "rename_prefixes": null, | |
| "include_names": null, | |
| "include_prefixes": null, | |
| "include_suffixes": null, | |
| "script_sha256": "129b4821dbc3cf7d01b5ce93e7672af1f90a057384df7ec89d2cf3eea4a9f3b5", | |
| "n_packs": 1, | |
| "total_pack_bytes": 253806796 | |
| } |