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
LoRA does not appear to work with your Model
#13
by cacarpenter - opened
I tried your Model, by itself, (16 ver) and it definitely changes a composition, highlighting faces and materials. Works pretty good, but less quality than the base Flux model.
Also, your LoRA, by itself, works ok, but lacks sharpness and detail.
But when I added in your LoRA with your Model to the ComfyUI process (I have a guaranteed working Flux-LoRA Workflow, uses LORAs perfectly from XLabs and Civitai), the output is just blurred.
Why would each work seperately but not together?
cacarpenter changed discussion title from LoRA does not appear to work to LoRA does not appear to work with your Model


