Tagged: stable-diffusion

36 articles

Latest

Stable Diffusion in 5 Lines of Python: Inside Diffusers' Text-to-Image Pipeline

Diffusers 0.3 adds Stable Diffusion to Macs with just 3.2GB VRAM

rinna fine-tunes Stable Diffusion for Japanese prompts and cultural nuance

Stable Diffusion Hits TPUs via JAX, Cuts Image Gen to 8 Seconds

Dreambooth Fine-Tuning: Low Learning Rates Beat Fast Results Every Time

Stable Diffusion's Architects Host Free Live Event on Nov 30

Apple's Core ML runs Stable Diffusion in 18s on M1 Max — here's the catch

Habana Gaudi2 cuts BERT training 5.75x vs first-gen in Hugging Face rerun

A Farming Game in 5 Days? This Dev Used Stable Diffusion to Nail the Art

LoRA cuts Stable Diffusion fine-tuning to 3MB files and 11GB GPUs

Stable Diffusion made a game-ready corn icon in under 10 minutes

Diffusers 1.1 doubles Stable Diffusion speed on Mac using Neural Engine

Hugging Face publishes ethics framework for Diffusers as bias concerns mount

ControlNet hits Diffusers: turn doodles into photos with 700M extra params

Inside the $1.10/hr A100 Run That Trained a ControlNet on 100K Synthetic Faces

Intel Sapphire Rapids CPUs cut Stable Diffusion inference from 45 seconds to 4.7

Stable Diffusion learns to derain, denoise, and cartoonize from text prompts

Intel's NNCF squeezes Stable Diffusion: 5.1x faster on CPUs with 4x smaller footprint

Hugging Face launches AI game jam as rivals ban generative tools

Apple's 6-bit Core ML trick makes Stable Diffusion 10-30% faster

Stable Diffusion Still Defaults to White, Male, and Western—Here's Why

Fine-tune Stable Diffusion with just 5 images on Intel CPUs

88 games, 1,300 devs: Inside the open-source AI game jam that crowned 'Snip It'

Hugging Face Diffusers turns 1 with SDXL, video pipelines, and 0.75-second CPU generation

OpenAI's Shap-E Can Now Generate Usable PS1-Style 3D Models

Segmind's open-source SD-Small and SD-Tiny slash Stable Diffusion size by up to 55%

T2I-Adapters Slim Down SDXL Control: 79M Params vs ControlNet's Bulk

Würstchen hits 42x image compression, slashing AI training costs 16-fold

Stable Diffusion gets RLHF-style fine-tuning with TRL's new DDPOTrainer

AI Comic Factory lets PRO users fork their own private comic generator

SDXL Drops From 72 Seconds to 11.4 on A100 With Two Line Changes

New LCM LoRA cuts SDXL image generation from 7 seconds to 1 on a 3090

Stable Diffusion 3.5 hits Diffusers with an 8B model and a 4-step turbo variant

45,000 Human Votes Rank Midjourney, DALL·E, and Stable Diffusion Head-to-Head

SegMoE packs 4 Stable Diffusion models into one pipeline — and prompt accuracy jumps

ONNX Runtime boosts SDXL Turbo image generation by 229% over PyTorch