With stable-diffusion-v1-4 it was possible to use the components of the pipeline independently, as explained in this very helpful tutorial: Stable Diffusion with 🧨 Diffusers In other words, one could write a custom pipeline by using the tokenizer, text encoder, unet, and vae one after another. I’m…

SDXL custom pipeline - Input to unet? - Why 2 text encoders?

ingo-m September 10, 2023, 9:24pm 5

@ClementP-XXII thanks for this information, I will try to use a custom pipeline by concatenating the encoder outputs.

Topic		Replies	Views
Did SDXL-inpainting fine-tune the text_encoder? Beginners	0	131	April 29, 2024
Use prompt tokens instead of prompt for sdxl? for the purpose of interpolation 🧨 Diffusers	0	203	April 2, 2024
Text_encoder_2, local model, not working 🧨 Diffusers	1	1333	May 25, 2024
Add additional trainable layers to StableDiffusion for fine-tuning 🧨 Diffusers	0	1018	October 8, 2023
Access CLIP from StableDiffusionPipeline and use the same models for multiple pipelines 🧨 Diffusers	3	2628	October 11, 2023