Instructions to use inclusionAI/TwinFlow with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use inclusionAI/TwinFlow with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("inclusionAI/TwinFlow", 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
- Draw Things
- DiffusionBee
How do I deploy this in ComfyUI? I really want to use it in ComfyUI, please help me.
#4
by Universe97 - opened
How do I deploy this in ComfyUI? I really want to use it in ComfyUI, please help me.
same process as every other image model bud. its just a transformer change meaning the diffusion model is incorporating the twinflow additive. at least from what i see its a standard image workflow using qwen architecture.
https://huggingface.co/Suzu008/TwinFlow_Repackaged/blob/main/TwinFlow-Qwen-Image-v1.0-BF16.safetensors
Please someone make GGUF ?)
For gguf, check this: https://huggingface.co/smthem/TwinFlow-Qwen-Image-v1.0-diffusers-gguf
For ComfyUI support, check this: https://github.com/smthemex/ComfyUI_TwinFlow