Working from home
Block or Report
Block or report patil-suraj
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
-
-
onnx_transformers Public
Accelerated NLP pipelines for fast inference on CPU. Built with Transformers and ONNX runtime.
-
exploring-T5 Public
A repo to explore different NLP tasks which can be solved using T5
893 contributions in the last year
Activity overview
Contributed to
huggingface/transformers,
huggingface/diffusers,
huggingface/bloom-jax-inference
and 15 other
repositories
Contribution activity
August 2022
Created 13 commits in 4 repositories
Created 3 repositories
- patil-suraj/stable-diffusion Jupyter Notebook
-
patil-suraj/stable-diffusion-jax
Python
•
Built by
- patil-suraj/SwinIR-JAX Python
Created a pull request in huggingface/diffusers that received 20 comments
Opened 13 other pull requests in 2 repositories
huggingface/diffusers
2
open
9
merged
- [POC] allow custom height, width in StableDiffusionPipeline.
- add tests for stable diffusion pipeline
- [LDM pipeline] fix eta condition.
- [PNDM in LDM pipeline] use inspect in pipeline instead of unused kwargs
- allow pndm scheduler to be used with ldm pipeline
- add scaled_linear schedule in PNDM and DDPM
- [LDMTextToImagePipeline] make text model generic
- add attention up/down blocks for VAE
- [VAE] fix the downsample block in Encoder.
- [UNet2DConditionModel] add cross_attention_dim as an argument
- [WIP] Latnet (and Stable) diffusion text2img conversion script.

Formed in 2009, the Archive Team (not to be confused with the archive.org Archive-It Team) is a rogue archivist collective dedicated to saving copies of rapidly dying or deleted websites for the sake of history and digital heritage. The group is 100% composed of volunteers and interested parties, and has expanded into a large amount of related projects for saving online and digital history.






