Users/droid/@gh ~ % man generative-art

GENERATIVE_ART(1)

NAME

generative art - brain dump for relevant research and datasheets

SYNOPSIS

generative-art [-v | --version][-h | --help][-r | --read][-q | --queue]
[-o <path>][--config=<path>] <command> [<args>]

DESCRIPTION

This is a reference list for programmers to find articles of interest and pinpoint exact formulae and techniques. Primarily pre-print ARXIV focused.

IMAGE SYNTHESIS (DIFFUSION, AUTOREGRESSIVE & VARIATIONAL AUTOENCODERS)

https://arxiv.org/abs/1312.6114 Variational Autoencoders
https://arxiv.org/abs/2112.10752 Latent Diffusion
https://arxiv.org/abs/2205.11487v1 Imagen
https://arxiv.org/abs/2209.03003 Rectified Flow
https://arxiv.org/abs/2211.01324 The Ensemble of Expert Denoisers
https://arxiv.org/abs/2212.09748 DiT
https://arxiv.org/abs/2303.13285 Fourier Diffusion Models
https://arxiv.org/abs/2306.00637 Würstchen
https://arxiv.org/abs/2307.01952 SDXL
https://arxiv.org/abs/2310.00426 Pixart-α
https://arxiv.org/abs/2310.12395 Closed-Form Score Generative Diffusion Models
https://arxiv.org/abs/2310.16825 CommonCanvas - Diffusion from Collective Commons images
https://arxiv.org/abs/2401.02677 Segmind SSD-1V & Vega
https://arxiv.org/abs/2401.05252 Pixart-δ
https://arxiv.org/abs/2402.13929 SDXL Lightning
https://arxiv.org/abs/2402.17245 Playground 2.5
https://arxiv.org/abs/2403.03206 Stable Diffusion 3
https://arxiv.org/abs/2403.04692 PixArt-Σ
https://arxiv.org/abs/2403.05121 CogView3
https://arxiv.org/abs/2403.13802 ZigMa DiT style Mamba-based Diffusion
https://arxiv.org/abs/2404.02905 VAR Autoregressive Modeling
https://arxiv.org/abs/2404.13686 Hyper-SD
https://arxiv.org/abs/2405.02730 U-Dit
https://arxiv.org/abs/2405.05945 Lumina T2X
https://arxiv.org/abs/2405.08748 HunYuan-DiT
https://arxiv.org/abs/2405.14224 State-Space Model DiM Diffusion Mamba
https://arxiv.org/abs/2406.18583 Lumina-Next (Next-DiT)
https://arxiv.org/abs/2408.11039 Transfusion Multimodal Prediction
https://arxiv.org/abs/2409.10695v1 Playground 3
https://arxiv.org/abs/2409.19946 Ilustrious
https://arxiv.org/abs/2410.11795 Efficiency Comparison and Overview of models ca Oct 2024
https://arxiv.org/abs/2412.04431 Infinity
https://arxiv.org/abs/2502.09992 Llada
https://arxiv.org/abs/2504.05741 Decoupled Diffusion Transformer (DDT)
https://arxiv.org/abs/2504.07963 PixelFlow
https://arxiv.org/abs/2510.11690 Diffusion Transformers with Representational Autoencoders
https://arxiv.org/abs/2510.21890 The Principles of Diffusion Models
https://arxiv.org/abs/2511.13720 Back to Basics, Let Denoising Generative Models Denoise
https://arxiv.org/abs/2505.07447v1 Unified Continuous Generative Models
https://arxiv.org/abs/2502.09509 EQ Vae (reducing equivariant symmetry errors)

ATTENTION

https://arxiv.org/abs/1406.2661 Generative Adversarial Networks
https://arxiv.org/abs/1505.04597 UNet Model
https://arxiv.org/abs/1512.03385 ResNet Model
https://arxiv.org/abs/1706.03762 the Transformer & attention
https://arxiv.org/abs/1711.10485 Attentional GAN
https://arxiv.org/abs/2103.14030 Swin Shifted windows Transformer
https://arxiv.org/abs/2108.01073 SDEdit
https://arxiv.org/abs/2112.05682v2 Self Attention Memory Efficiency
https://arxiv.org/abs/2205.14135 Flash Attention
https://arxiv.org/abs/2211.12572 Plug & Play I2I Translation
https://arxiv.org/abs/2307.08691 Flash Attention 2: Attention Boogaloo
https://arxiv.org/abs/2312.06635 GLA Gated Linear Attention Transformer
https://arxiv.org/abs/2405.18428 DiG Diffusion-Gated Linear Attention Transformer
https://arxiv.org/abs/2406.08552 DiTFastAttn: Attention Compression
https://arxiv.org/abs/2407.08608 Flash Attention 3: The Flash Crusade
https://arxiv.org/abs/2411.06558 Region-Aware Generation Diffusion, improved composition

GUIDANCE

https://arxiv.org/abs/2207.12598 Classifier Free Guidance
https://arxiv.org/abs/2210.00939 Self-Attention Guidance
https://arxiv.org/abs/2301.12247 Semantic Guidance
https://arxiv.org/abs/2301.13826 Attend-and-excite Attention Guidance, Generative Semantic Nursing
https://arxiv.org/abs/2404.07724 Interval Guidance
https://arxiv.org/abs/2406.02507 CFG Analysis
https://arxiv.org/abs/2506.10978 Fine-Grained Perturbation Guidance via Attention Head Selection

SCHEDULERS

https://arxiv.org/abs/2006.11239 DDPM Denoising Diffusion Probabilistic Models
https://arxiv.org/abs/2010.02502v4 DDIM Denoising Diffusion Implicit Models
https://arxiv.org/abs/2011.13456 SDE Stochastic Differential Equations
https://arxiv.org/abs/2102.09672 DDPM optimizing
https://arxiv.org/abs/2105.14080 adaptive SDE
https://arxiv.org/abs/2202.09778 PNDM Solving Pseudo linear multi-step Numerical Diffusion Models on manifolds
https://arxiv.org/abs/2206.00364 Euler scheduler (Algorithm 2) / Heun / Karras / DPMa SDE
https://arxiv.org/abs/2206.00927 DPM Solver
https://arxiv.org/abs/2210.02747 Flow Matching
https://arxiv.org/abs/2211.01095 DPM Solver ++
https://arxiv.org/abs/2302.04867 UniPC Sampler
https://arxiv.org/abs/2305.08891 V Prediction with Zero SNR And CFG Rescale
https://arxiv.org/abs/2404.14507 Align Your Steps
https://arxiv.org/abs/2406.03293 Rectified Flow
https://arxiv.org/abs/2412.06264 Flow Matching Guide and Code
https://arxiv.org/abs/2503.10772 FlowTok
https://arxiv.org/abs/2506.14603 Align Your Flow

LANGUAGE MODELS

https://arxiv.org/abs/1910.10683 T5 Text-to-Text Transfer Transformer
https://arxiv.org/abs/2010.11929 ViT Vision Transformer
https://arxiv.org/abs/2103.00020 Natural Language Supervision training
https://arxiv.org/abs/2106.04560 ViT Scaling
https://arxiv.org/abs/2112.10003 CLIPSeg
https://arxiv.org/abs/2205.11487 Photorealistic Language models, Imagen & DrawBench benchmark
https://arxiv.org/abs/2211.06679 ALTCLIP
https://arxiv.org/abs/2311.14284 Paragraph to Image using LLM Models
https://arxiv.org/abs/2403.08857 Evaluating Multi-Modal LLMs
https://arxiv.org/abs/2406.06525 Llama for Scalable Image Generation (Autoregressive Vs Diffusion)
https://arxiv.org/abs/2408.05636 SpecDiff Accelerating Language Generation through speculative diffusion decoding
https://arxiv.org/abs/2502.13967 FlexTok 1D Token Latent Image Reconstruction
https://arxiv.org/abs/2506.10892 Duo The Diffusion Duality
https://arxiv.org/abs/2512.19941 Block-Recurrent Dynamics in Vision Transformers

IMAGE RESTORATION/SUPER RESOLUTION MODELS

https://arxiv.org/abs/1802.05957 GAN Color Normalization
https://arxiv.org/abs/2107.10833 RealESRGAN
https://arxiv.org/abs/2108.10257 SwinIR
https://arxiv.org/abs/2401.13627 SUPIR

OPTIMIZATIONS

https://arxiv.org/abs/1711.07837 UnFlow unsupervised training
https://arxiv.org/abs/2110.02861 8 bit optimizers with 32 bit performance
https://arxiv.org/abs/2202.00512 Distillation
https://arxiv.org/abs/2207.04316 Patching diffusion models to increase efficiency
https://arxiv.org/abs/2208.01618 Textual Inversion
https://arxiv.org/abs/2208.12242 DreamBooth training
https://arxiv.org/abs/2302.05442 ViT 22b Scaling
https://arxiv.org/abs/2302.05543 ControlNET
https://arxiv.org/abs/2302.08453 T2i Adapter
https://arxiv.org/abs/2303.06555 UniDiffuser
https://arxiv.org/abs/2304.02643 SAM Segment Anything
https://arxiv.org/abs/2305.08891 ZSNR Zero signal-to-noise
https://arxiv.org/abs/2305.10973 DragGAN Diffusion Manifold manipulation
https://arxiv.org/abs/2307.02421 DragonDiffusion Drag Editing
https://arxiv.org/abs/2309.11497 FreeU
https://arxiv.org/abs/2310.04378 LCM
https://arxiv.org/abs/2311.05556 LCM-LoRA
https://arxiv.org/abs/2311.17137 Intrinsic LoRA
https://arxiv.org/abs/2312.00858v2 DeepCache
https://arxiv.org/abs/2312.02238 X-Adapter modular model mapping
https://arxiv.org/abs/2312.12491 StreamDiffusion real time generating and modifying
https://arxiv.org/abs/2401.11605 Scalable Image Synthesis via Hourglass Diffusion
https://arxiv.org/abs/2402.19159 TCD Trajectory Consistency Distillation
https://arxiv.org/abs/2404.10177 Corrupted data training
https://arxiv.org/abs/2405.14430 PipeFusion parallel DiT processing
https://arxiv.org/abs/2405.18407 PCM Phased Consistency
https://arxiv.org/abs/2406.04314 SPO
https://arxiv.org/abs/2406.06911 Async Denoising Parallel Diffusion
https://arxiv.org/abs/2406.09416 Scaling detail w multiple networks and normalization to prevent distortions
https://arxiv.org/abs/2406.10163 Pd Mesh
https://arxiv.org/abs/2407.02158 UltraPixel 4k-6k image generation
https://arxiv.org/abs/2408.05446 Ensemble Everything Everywhere: Multi-scale aggregation for adversarial robustness
https://arxiv.org/abs/2410.23054v1 Controlling Language and Diffusion Models by Transporting Activations
https://arxiv.org/abs/2503.07565 Inductive MOment Matching
https://arxiv.org/abs/2504.10483 REPA-E VAE training
https://arxiv.org/abs/2504.17789 Token Shuffle autoregressive image synthesis token reduction
https://arxiv.org/abs/2505.13447 One step Generative Modeling
https://arxiv.org/abs/2511.19797 TVM Terminal Velocity Matching
https://arxiv.org/abs/2512.15603 Qwen-Image-Layered
https://arxiv.org/abs/2512.15657 SoFlow One Step Generative Modeling

ADVERSARIAL PERTURBATIONS

https://arxiv.org/abs/2302.04222 Glaze
https://arxiv.org/abs/2302.04578 MIST/AdvDM Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models
https://arxiv.org/abs/2302.06588 Photoguard
https://arxiv.org/abs/2303.15433 AntiDreambooth
https://arxiv.org/abs/2310.13828 Nightshade
https://arxiv.org/abs/2311.13127 MetaCloak
https://arxiv.org/abs/2312.07865 SimAC
https://arxiv.org/abs/2405.20584 AdvDM/DisDif Disrupting Diffusion Via Token-Level Attention Erasure
https://arxiv.org/abs/2409.08167 HF-Anti Dreambooth
https://arxiv.org/abs/2412.11638 IDProtector
https://dl.acm.org/doi/abs/10.1145/3503161.3547923 StyleGAN Inversion

FACIAL PRIVACY

https://arxiv.org/abs/2112.09151 TAFIM: Targeted Adversarial Attacks against Facial Image Manipulations
https://dl.acm.org/doi/abs/10.1145/3503161.3547923 Defeating DeepFakes via Adversarial Visual Reconstruction
https://arxiv.org/abs/2305.13625 DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection
https://arxiv.org/abs/2309.05330 DiffPrivate: Facial Privacy Protection with Diffusion Models
https://ieeexplore.ieee.org/document/10688292 SD4Privacy: Exploiting Stable Diffusion for Protecting Facial Privacy
https://arxiv.org/abs/2503.10350 Enhancing Facial Privacy Protection via Weakening Diffusion Purification

ANTI-ADVERSARIAL PERTURBATIONS
https://arxiv.org/abs/2205.07460 DiffPure
https://arxiv.org/abs/2312.00084 GrIDPure Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
https://arxiv.org/abs/2406.12027 Adversarial Perturbations Cannot Reliably Protect Artists
https://arxiv.org/abs/2511.10382v1 AntiDB Purify

MISC

https://arxiv.org/abs/1603.09382 stochastic depth training
https://arxiv.org/abs/1611.07004 pix2pix
https://arxiv.org/abs/1806.02658 Super resolution particulars
https://arxiv.org/abs/1810.12890 Managing dropout on layers using DropBlock]
https://arxiv.org/abs/1811.11718 Convolution Padding VS Zero Padding
https://arxiv.org/abs/1812.06162 Model training observations
https://arxiv.org/abs/1908.04913 Fair face
https://arxiv.org/abs/1910.04867 VTAB benchmark
https://arxiv.org/abs/1910.09700 Quantifying the Carbon Emissions of Machine Learning
https://arxiv.org/abs/1912.11945 On the Morality of Artificial Intelligence
https://arxiv.org/abs/2010.14701 Generative Scaling Laws and Relation
https://arxiv.org/abs/2105.05233 Comparative study of diffusion and GAN
https://arxiv.org/abs/2208.11695 How ImageNet Misrepresents Biodiversity
https://arxiv.org/abs/2210.05559 CycleDiffusion Image2Image
https://arxiv.org/abs/2211.13227 Exemplar Based I2I Inpainting
https://arxiv.org/abs/2303.06219v1 The Carbon Emissions of Writing and Illustrating Are Lower for AI than for Humans
https://arxiv.org/abs/2303.13439 Pix2Pix vid gen
https://arxiv.org/abs/2306.07154 InstructPix2Pix
https://arxiv.org/abs/2401.14423 Advanced Prompt Engineering
https://arxiv.org/abs/2403.01779 OOTD clothing try on
https://arxiv.org/abs/2403.12171 EasyJailbreak
https://arxiv.org/search/cs?searchtype=author&query=Luccioni,+A All of this person's work is incredible tbh

ALTERNATIVE RESOURCES

https://lilianweng.github.io/posts/2021-07-11-diffusion-models/ Concentrated quality, in-depth information
https://github.com/ponyzym/Efficient-Diffusion-Models-Survey Comparative list of diffusion models

RELATED COLLECTIONS
https://github.com/gpu-mode/awesomeMLSys Like a greatest hits collection, but for GPUs
https://github.com/BestJunYu/Awesome-Physics-aware-Generation Physics-specific paper collection
https://github.com/thubZ09/All-Things-Multimodal Solid Multimodal Source
https://github.com/pliang279/awesome-multimodal-ml Huge multimodal paper collection
https://github.com/hindupuravinash/the-gan-zoo Very thorough GAN paper collection
https://www.ibm.com/think/topics/diffusion-models Technical but brief overview of Diffusion models
https://github.com/christianversloot/machine-learning-articles Moar
https://huggingface.co/blog/TimothyAlexisVass/explaining-the-sdxl-latent-space SDXL Specific details
https://github.com/neobundy/Deep-Dive-Into-AI-With-MLX-PyTorch/tree/master/deep-dives MLX architecture
https://github.com/kyegomez/EXA-1 Very large but dated paper collection
https://blog.fal.ai/auraflow/
https://blog.segmind.com/segmind-vega-2/
https://stable-diffusion-art.com/samplers/
https://ostris.com/2024/09/07/skipping-flux-1-dev-blocks/ Skipping blocks in flux
https://github.com/fal-ai/f-lite/blob/main/assets/F%20Lite%20Technical%20Report.pdf Fal F-Lite