mortenjust/native-diffusion

Support for Stable Diffusion 2.0

Open

#9 opened on Nov 24, 2022

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Swift (33 forks)github user discovery
help wanted

Repository metrics

Stars
 (494 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

2.0 just came out today. Blog post, repo

Highlights

  • Generate 768x768 images (weights)
  • New Upscaler model that can scale up to 4x in one go (weights)
  • Depth to image for shape-preserving img2img
  • Improved inpainting (weights)

We probably want to support both 2.0 and 1.5

Contributor guide

Research direction
Examine the current model loading code for Stable Diffusion 1.5 and adapt it to support the new 2.0 checkpoint format. Pay attention to the differences in the UNet configuration and the new text encoder (OpenCLIP).
Tech stack
swift
Domain
mobile devdesktop dev
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
SwiftXcodeMachine Learning Basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40