Instructions to use UmeAiRT/ComfyUI-Auto-Installer-Assets with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use UmeAiRT/ComfyUI-Auto-Installer-Assets with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("UmeAiRT/ComfyUI-Auto-Installer-Assets", 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
Download models/LLM/Florence-2-base-PromptGen-v2.0/tokenizer.json from UmeAiRT/ComfyUI-Auto-Installer-Assets: direct link, hf CLI and curl.
- Browser
- Download file 2.3 MB
-
https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/73b7161c2aa8e18def568ce25c247db38f422f88/models/LLM/Florence-2-base-PromptGen-v2.0/tokenizer.json
- Command line
-
hf download hf://UmeAiRT/ComfyUI-Auto-Installer-Assets@73b7161c2aa8e18def568ce25c247db38f422f88/models/LLM/Florence-2-base-PromptGen-v2.0/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/UmeAiRT/ComfyUI-Auto-Installer-Assets/resolve/73b7161c2aa8e18def568ce25c247db38f422f88/models/LLM/Florence-2-base-PromptGen-v2.0/tokenizer.json
2.3 MB
File too large to display, you can check the raw version instead.