Instructions to use byliutao/Longcat-Image-Turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use byliutao/Longcat-Image-Turbo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("byliutao/Longcat-Image-Turbo", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
ComfyUI support?
Do you know if this model has ComfyUI support yet?
Thanks for your attention. This is a ComfyUI version provided by the community: https://huggingface.co/jayn7/LongCat_Image_Turbo_Comfy_repackaged
Will you ever consider doing Continuous-Time Distribution Matching (CDM) on a high quality anime open source model called circlestone-labs/Anima? As it has a turbo Lora but it's makes the quality and details a bit worse.
Hey! Thanks for the suggestion.
We totally get the frustration with the Turbo LoRa degrading the quality and details on Anima, but unfortunately, we don't have any plans to do CDM on it right now. Our hands are tied with other projects at the moment.
Really appreciate you reaching out, though!