Text-to-Image
Diffusers
ONNX
Safetensors
English
StableDiffusionXLPipeline
common-canvas
stable-diffusion
sdxl
Inference Endpoints

I'm having trouble generating images that follow the prompt.

#3
by njasa - opened

image.png

njasa changed discussion title from I'm having trouble generating images with prompt following. to I'm having trouble generating images that follow the prompt.
njasa changed discussion status to closed
This comment has been hidden
This comment has been hidden
CommonCanvas org
edited May 19

The bigger issue is that it doesn't do as well on abstract noun because the captioner is less likely to tag them and instead of pick a more descriptive description. You can try a more specific prompt like a "a man standing in a room" and it works significantly better. It would be less likely to use more general concepts like "person" or other words for which a more descriptive noun exists:
image.png

Sign up or log in to comment