cog-sdxl
cog-sdxl copied to clipboard
replicate
Stable Diffusion XL training and inference as a cog model
CI⚡️CD
Working CI/CD + Error monitoring! Specifics: - CI builds and pushes a model to a staging model on Replicate, then runs integration tests. - The same tests will run both...
When setting `refiner=base_image_refiner`, the `refine_steps` argument promises to control how many denoising steps will be performed with the refiner:  However, in practice, this...
https://github.com/damian0815/compel#compel https://github.com/huggingface/diffusers/issues/2136
We're consistently getting crashes in the training script if we submit a comma in the token_string Failing training model `https://replicate.com/p/e76k0ze9a9rgm0cf1cftefcr0m?input=form` ``` Traceback (most recent call last): File "/usr/local/lib/python3.9/site-packages/cog/server/worker.py", line 217,...
Some changes have been made for users who want to deploy the trainable model by pushing it to replicate.com. If these changes are not made, the following error is encountered:...
Deploying a custom model works, but for sites with low traffic the cold-boot can be painfully long. I'm curious if we could add an optional parameter that'd point to a...
Using the built-in upcast fixed vae, fine details like hair come out fuzzy and pixelated. This is particularly present if cog-sdxl is used to generate a full fine tune and...
this uses https://github.com/technillogue/nyacomp to accelerate loading. it features nvCOMP bindings and tricks to start downloading and loading weights in parallel with python code. it can achieve load times as low...
Hi, I have been trying to load fine-tuned SDXL models to Automatic1111. When running the inference on Replicate, it works correctly. I downloaded the weights of the model and uploaded...
I am using this model for some specific use cases via the Replicate API. I know that I can fork this and create my own version, but I only have...
