-
CrossAttentionControl
Unofficial implementation of "Prompt-to-Prompt Image Editing with Cross Attention Control" with Stable Diffusion
-
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
Is this one https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py using the crude approximation?
Wonder if the inversion code could be used to style transfer like in https://github.com/justinpinkney/stable-diffusion . Take clip1 embedding from image1, reconstruct the noise1, take image 2, find clip2, and recreate from noise1 to get a style2 result. Still only just read about it so haven't thought it through, but the reconstruction idea seemed very useful. I will think about it but i'm not sure i'm up to the task of coding it up/trying it out myself