Instructions to use Shakker-Labs/AWPortrait-FL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Shakker-Labs/AWPortrait-FL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Shakker-Labs/AWPortrait-FL", 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
why comfyui report: ERROR: Could not detect model type of: D:\ComfyUI\models\checkpoints\AWPortrait-FL-fp8.safetensors
using flux1-dev-fp8.safetensors in comfyui is ok, but AWPortrait-FL-fp8.safetensors reported this error.
how to solve?
thanks
Please make sure you put the model in the right folder.
Please make sure you put the model in the right folder.
so one AWPortrait-FL-fp8.safetensors is enough?
i'll try to re-download
AWPortrait-FL-fp8.safetensors must be wrong.
1)using the latest comfyui
2) flux1-dev-fp8.safetensors and AWPortrait-FL-fp8.safetensors in the same folder
3)flux works, but awportrait reports: "ERROR: Could not detect model type"
do you use "Load checkpoints model" node , you should use "Load Diffusion model" and "DualCLIPLoader"
do you use "Load checkpoints model" node , you should use "Load Diffusion model" and "DualCLIPLoader"
yes i used "Load checkpoints model" nod
how to use "Load Diffusion model" to load a safetensors like AWPortrait-FL-fp8.safetensors? it only have option of "flux.1-schnell-dev-merged-fp8.safetensors".
do you use "Load checkpoints model" node , you should use "Load Diffusion model" and "DualCLIPLoader"
thank you!
i move awportrait-fl to diffusion folder and add a vae node then it works.