Instructions to use Hippotes/Ideogram4-Fal-ComfyUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Hippotes/Ideogram4-Fal-ComfyUI with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Hippotes/Ideogram4-Fal-ComfyUI", torch_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
difference between fast and instant?
#2
by realrebelai - opened
is this an inference based speed up or a compression based speed up?
instant is 8-step, fast is 20-step. Both CFG 1. It is also trained with NVFP4 quantization in mind (quantization aware distillation).
more info:
https://huggingface.co/fal/ideogram-v4-fast
https://huggingface.co/fal/ideogram-v4-instant
instant is 8-step, fast is 20-step. Both CFG 1. It is also trained with NVFP4 quantization in mind (quantization aware distillation).
more info:
https://huggingface.co/fal/ideogram-v4-fast
https://huggingface.co/fal/ideogram-v4-instant
thank you for the reply and thank you for the contribution!
