Diffusers Adds Native LoRA Training Scripts and FP8/NVFP4 Quantized Inference
RisingSayak · x · 2026-10-15
Diffusers now ships Diffusers-native LoRA training scripts for both text-to-image and image-to-image, contributed by @linoytsaban, and can load LoRAs trained with @ostrisai's ai-toolkit.
Both distilled and non-distilled pipelines are implemented as modular diffusers pipelines for maximum flexibility. The team also added support for loading quantized checkpoints (FP8r and NVFP4) and running inference with them, giving them a dedicated backend.
Related event: Black Forest Labs Releases Flux.3 Klein with Day-0 Diffusers Support(4 posts)→
More from coding & agent
- Vercel Goes Full Backend: Python GA, Containers, and Daemons — cramforce · 2026-10-16
- WorldMemArena Accepted at NeurIPS: Memory Storage ≠ Memory Use — xwang_lk · 2026-10-16
- Vercel Ship Demos Container Deploys for Go, Ruby, Java and More — edwin · 2026-10-16
- TRL adds day-0 support for fine-tuning Muse Spark Open's 816B MoE with LoRA on 64 H100s — QGallouedec · 2026-10-16
- Databricks engineers land impactful PRs on day 2 with AI dev tools, vs week 3 before — Yuchenj_UW · 2026-10-16
- Perplexity open-sources SPACE, the sandbox platform powering its Computer agents — AravSrinivas · 2026-10-16