SLD (Self-correcting LLM-controlled Diffusion Models)

Official implementation of the self-correcting LLM-controlled diffusion model

CommonProductImageImage GenerationAI Art

SLD is a self-correcting LLM-controlled diffusion model framework that achieves precise text-to-image alignment by integrating a detector-enhanced generator. The SLD framework supports both image generation and fine-grained editing, and is compatible with any image generator, such as DALL-E 3, without requiring additional training or data.

Best AI Websites & Tools

SLD (Self-correcting LLM-controlled Diffusion Models)

SLD (Self-correcting LLM-controlled Diffusion Models) Visit Over Time

SLD (Self-correcting LLM-controlled Diffusion Models) Visit Trend

SLD (Self-correcting LLM-controlled Diffusion Models) Visit Geography

SLD (Self-correcting LLM-controlled Diffusion Models) Traffic Sources

SLD (Self-correcting LLM-controlled Diffusion Models) Alternatives

Pony Diffusion — A versatile text-to-image diffusion model that generates high-quality non-photorealistic images.

flux-controlnet-canny — A text-to-image generation model based on ControlNet

FLUX.1-dev — A text-to-image generation model with 1.2 billion parameters

SDXL Flash — A high-performance text-to-image generation model

PIXART — PIXART-Σ is a diffusion transformer model (Diffusion Transformer) for generating 4K text-to-image.

RECE — A concept erasure technology for text-to-image diffusion models.

AuraFlow v0.3 — Open-source text-to-image generation model

flux-lora-collection — A collection of text-to-image generation models

flux-RealismLora — LoRA text-to-image generation technology based on the FLUX.1-dev model.

AI Drawing Pro — AI image generator for one-click art creation

Mann-E Art — An image generation model based on Stable Diffusion XL

Adobe Firefly Vector AI — Creative Generative AI Tool

AuraFlow — An open-source, streaming-based text-to-image generation model

RodinHD — High-Fidelity 3D Avatar Generation Model

ComfyUI-KwaiKolorsWrapper — A Diffusers wrapper for the Kwai-Kolors text-to-image model.

Kolors — A large-scale text-to-image generation model based on latent diffusion models

Midsommar Cartoon — Retro-style cartoon model, blending anime and Scandinavian cartoon elements.

AsyncDiff — An asynchronous denoising parallelized diffusion model

InstantX — AI Content Generation Research Organization

Illustration Generator — AI-powered image generator for creating professional illustrations with one click.

LlamaGen — A new breakthrough in autoregressive models for scalable image generation

HyperDreamBooth — Fast Personalized Text-to-Image Model

Era3D — High-resolution multi-view diffusion model using an efficient row attention mechanism.

Slicedit — Text-based video editing technology using spatiotemporal slicing.

MuLan — MuLan: A Multi-Language Diffusion Model Adaptable for 110+ Languages

Lumina-T2X — A unified text-to-any-modal generation framework

IDM-VTON — A diffusion model designed for virtual try-on tasks, particularly enhancing image fidelity and detail preservation in real-world scenes.

Imagine Flash — Generate high-fidelity, diverse samples with minimal steps.