Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
Instructions to use CompVis/stable-diffusion-v1-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use CompVis/stable-diffusion-v1-4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", dtype=torch.bfloat16, device_map="cuda") prompt = "A high tech solarpunk utopia in the Amazon rainforest" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Missing mention of gender bias in Model Card
#67
by trafagar - opened
When I test out the model, any mention of profession such as engineer, data scientist, data engineer, programmer resulted in mostly male looking images while some profession like nurse, teacher, assistants, secretaries, hairdressers, cosmetologists resulted in mostly female looking images. If you have the bias section in the model card and you did mention about race and culture bias, this should be mentioned too.
That is what NN learned from the media in the input set ... you can't blame this bias on a model. Blame it on humanity and the media content it creates.