Stability-AI/sd3.5

• highabout#1

  Add a concise repository description

  Why:

  COPY-PASTE FIX

  Copy

  Inference-only reference implementation for Stable Diffusion 3.5 and SD3, including support for SD3.5 Large ControlNets. Designed for partner organizations and developers integrating SD3.5/SD3.

  OpenDoneDismiss
• mediumreadme#2

  Refine the README's opening paragraph for clarity and differentiation

  Why:

  CURRENT

  # Stable Diffusion 3.5
  
  Inference-only tiny reference implementation of SD3.5 and SD3 - everything you need for simple inference using SD3.5/SD3, as well as the SD3.5 Large ControlNets, excluding the weights files.
  
  Contains code for the text encoders (OpenAI CLIP-L/14, OpenCLIP bigG, Google T5-XXL) (these models are all public), the VAE Decoder (similar to previous SD models, but 16-channels and no postquantconv step), and the core MM-DiT (entirely new).
  
  Note: this repo is a reference library meant to assist partner organizations in implementing SD3.5/SD3. For alternate inference, use Comfy.

  COPY-PASTE FIX

  Copy

  # Stable Diffusion 3.5 Reference Implementation
  
  This repository provides an inference-only reference implementation for Stable Diffusion 3.5 and SD3, including support for SD3.5 Large ControlNets. It contains all necessary code for simple inference, excluding the model weights themselves. This library is specifically designed to assist partner organizations and developers in integrating SD3.5/SD3 into their applications, offering a foundational codebase for advanced customization. For general-purpose inference with a user interface, consider tools like ComfyUI.
  
  The implementation includes code for the text encoders (OpenAI CLIP-L/14, OpenCLIP bigG, Google T5-XXL), the VAE Decoder (16-channels, no postquantconv step), and the core MM-DiT.

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  What open-source libraries offer a reference implementation for generative image model inference?

  you: not recommended
  AI recommended (in order):

  1. Diffusers (huggingface/diffusers)
  2. PyTorch Hub
  3. TensorFlow Hub
  4. KerasCV (keras-team/keras-cv)
  5. MMGeneration (open-mmlab/mmgeneration)
  6. latent-diffusion (CompVis/latent-diffusion)
  7. StyleGAN3 (NVlabs/stylegan3)

  AI recommended 7 alternatives but never named Stability-AI/sd3.5. This is the gap to close.

  Show full AI answer
• CATEGORY QUERY

  Seeking tools to implement text-to-image generation using diffusion models and ControlNets.

  you: not recommended
  AI recommended (in order):

  1. Hugging Face Diffusers
  2. Automatic1111 Stable Diffusion Web UI
  3. ComfyUI
  4. PyTorch
  5. KerasCV

  AI recommended 5 alternatives but never named Stability-AI/sd3.5. This is the gap to close.

  Show full AI answer

• Metadata completeness

  fail

  Suggestion:

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of Stability-AI/sd3.5?

  pass
  ✓AI named Stability-AI/sd3.5 explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• If a team adopts Stability-AI/sd3.5 in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named Stability-AI/sd3.5 explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• In one sentence, what problem does the repo Stability-AI/sd3.5 solve, and who is the primary audience?

  pass
  ✓AI named Stability-AI/sd3.5 explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?