Image generation support!

Changes

• Image generation support: Generate images with diffusers models like Z-Image-Turbo in a new "Image AI" tab. Features include:
  • 4bit/8bit quantization
  • torch.compile support
  • LLM-generated prompt variations
  • PNG metadata for generation settings
  • Gallery for past generations
  • Progress bar
  • OpenAI-compatible API endpoint for image generation

For a step-by-step tutorial, consult: Image Generation Tutorial

• Pass bos_token and eos_token to jinja2 templates, making it possible to use the template for Seed-OSS-36B-Instruct and other models
• Use flash_attention_2 by default for Transformers models

Bug fixes

• Fix API requests always returning the same created time

Backend updates

• Update llama.cpp to https://github.com/ggml-org/llama.cpp/tree/0a540f9abd98915edb99fed47d80078ed8d2f343
• Update ExLlamaV3 to 0.0.17

Portable builds

Below you can find self-contained packages that work with GGUF models (llama.cpp) and require no installation! Just download the right version for your system, unzip, and run.

Which version to download:

• Windows/Linux:

  • NVIDIA GPU: Use cuda12.4.
  • AMD/Intel GPU: Use vulkan builds.
  • CPU only: Use cpu builds.

• Mac:

  • Apple Silicon: Use macos-arm64.

Updating a portable install:

1. Download and unzip the latest version.
2. Replace the user_data folder with the one in your existing install. All your settings and models will be moved.