Image & Video Generation
Diffusion models, Stable Diffusion, ComfyUI, text-to-image/video
272 articles across 100 editions
Articles
- Ling-2.5-1T: 1T Parameter Open-Source Instant Model with 1M Context -- 2026-02-16
- Qwen3.5-397B-A17B Unsloth GGUFs — Run on Consumer Hardware -- 2026-02-16
- Running Qwen3-Coder-Next 80B on 8GB VRAM — 300x Speedup via Custom Expert Caching -- 2026-02-16
- Flame Graphs vs Tree Maps vs Sunburst (2017) -- 2025-12-31
- 39C3: Recreating Sandstorm -- 2025-12-31
- EditMGT — fast, localized image editing with Masked Generative Transformers -- 2025-12-30
- Francis-Rings/FlashPortrait -- 2025-12-30
- zai-org/GLM-TTS -- 2025-12-30
- Flowception: Temporally Expansive Flow Matching for Video Generation -- 2025-12-30
- Key Highlights of NVIDIA’s New Model: Nemotron 3 -- 2025-12-17
- The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator -- 2025-12-17
- ostris/Z-Image-De-Turbo -- 2025-12-12
- zai-org/GLM-TTS -- 2025-12-11
- openbmb/VoxCPM1.5 -- 2025-12-11
- ByteDance-Seed/Depth-Anything-3 -- 2025-12-10
- seominseok0429/Upsample-Anything-A-Simple-and-Hard-to-Beat-Baseline-for-Feature-Upsampling -- 2025-12-09
- lrzjason/QwenEdit-Anything2Real_Alpha -- 2025-12-08
- How Big is Your Video Again? Square vs Rectangular Pixels -- 2025-12-08
- shubh-io/DockMate -- 2025-12-08
- Comfy-Org/HunyuanVideo_1.5_repackaged -- 2025-12-08
- ByteDance/BindWeave -- 2025-12-08
- apple/starflow -- 2025-12-04
- princepainter/ComfyUI-PainterLongVideo -- 2025-12-04
- OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing -- 2025-12-03
- Z-Image: Powerful and highly efficient image generation model with 6B parameters -- 2025-12-03
- FLUX.2: Frontier Visual Intelligence -- 2025-11-28
- Diffusers welcomes FLUX-2 -- 2025-11-26
- dx8152/Relight -- 2025-11-26
- Question About Motherboards -- 2025-11-26
- Qwen/Qwen3-VL-4B-Instruct -- 2025-11-20
- Soul-AILab/SoulX-Podcast-1.7B -- 2025-11-20
- wildminder/ComfyUI-DyPE -- 2025-11-19
- lightx2v/Autoencoders -- 2025-11-19
- We ran over 600 image generations to compare AI image models -- 2025-11-13
- dx8152/Qwen-Image-Edit-2509-Relight -- 2025-11-13
- meituan-longcat/LongCat-Video -- 2025-11-05
- allenai/olmOCR-2-7B-1025-FP8 -- 2025-11-05
- deepseek-ai/DeepSeek-OCR -- 2025-11-04
- LiquidAI/LFM2-VL-3B -- 2025-11-04
- Qwen/Qwen3-VL-235B-A22B-Thinking -- 2025-11-04
- DeepSeek may have found a new way to improve AI’s ability to remember -- 2025-11-02
- Qwen/Qwen3-VL-8B-Thinking -- 2025-11-02
- nvidia/omnivinci -- 2025-11-02
- OpenImagingLab/FlashVSR -- 2025-11-02
- Build Your Own Force-Feedback Joystick -- 2025-11-02
- ZOZO's Contact Solver for physics-based simulations -- 2025-11-01
- valiantcat/Qwen-Image-Edit-MeiTu -- 2025-11-01
- ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing -- 2025-11-01
- fireleyfreya/AI-Art-Generator -- 2025-10-30
- krea/krea-realtime-video -- 2025-10-30
- Cerebras REAP'd GLM4.6: 25%, 30%, 40% pruned FP8 checkpoints on HF! -- 2025-10-28
- Qwen/Qwen3-VL-30B-A3B-Instruct-FP8 -- 2025-10-28
- lightx2v/Wan2.2-Distill-Loras -- 2025-10-28
- GPT-OSS-20b TAKE THE HELM! Further experiments in autopilot. -- 2025-10-28
- 5060ti chads... ram overclocking, the phantom menace -- 2025-10-28
- Batch inference locally on 4080 -- 2025-10-28
- DeepSeek just released a bombshell AI model (DeepSeek AI) so profound it may be as important as the initial release of ChatGPT-3.5/4 ------ Robots can see-------- And nobody is talking about it -- And it's Open Source - If you take this new OCR Compresion + Graphicacy = Dual-Graphicacy 2.5x improve -- 2025-10-27
- Pico Banana: Large-Scale Dataset for Image Editing by Apple -- 2025-10-27
- dvlab-research/DreamOmni2 -- 2025-10-25
- bytetriper/RAE -- 2025-10-25
- tencent/POINTS-Reader -- 2025-10-25
- Stitch: Training-Free Position Control in Multimodal Diffusion Transformers -- 2025-10-25
- Llama.cpp is looking for M5 Neural Accelerator performance testers -- 2025-10-24
- NVIDIA sent me a 5090 so I can demo Qwen3-VL GGUF -- 2025-10-24
- AMD ROCm 7.9 and dwindling GPU support -- 2025-10-24
- Show HN: Cuq – Formal Verification of Rust GPU Kernels -- 2025-10-24
- [Editorial] https://github.com/DrewThomasson/ebook2audiobook -- 2025-10-23
- [Editorial] https://github.com/lfnovo/open-notebook -- 2025-10-23
- tencent/Hunyuan3D-Omni -- 2025-10-23
- Doby-Xu/WithAnyone -- 2025-10-22
- lightx2v/Wan2.2-I2V-A14B-Moe-Distill-Lightx2v -- 2025-10-22
- mit-han-lab/streaming-vlm -- 2025-10-22
- tencent-ailab/SongPrep -- 2025-10-20
- opendatalab/MinerU2.5-2509-1.2B -- 2025-10-20
- QuantStack/Qwen-Image-Edit-2509-GGUF -- 2025-10-20
- LM Studio and VL models -- 2025-10-19
- Qwen/Qwen-Image-Edit-2509 -- 2025-10-19
- Alpha-VLLM/Lumina-DiMOO -- 2025-10-19
- linkedlist771/SoraWatermarkCleaner -- 2025-10-19
- Audio transcription with llama.cpp multimodal -- 2025-10-18
- I built a fully automated AI podcast generator that connects to ollama -- 2025-10-18
- Paper2Video — turn a research paper into a full presentation video (slides, speech, talking head) -- 2025-10-15
- Practical OCR with Nanonets OCR2‑3B -- 2025-10-15
- neuphonic/neutts-air -- 2025-10-15
- Qwen/Qwen3-VL-235B-A22B-Instruct -- 2025-10-15
- XiaomiMiMo/MiMo-Audio-Eval -- 2025-10-15
- Very interesting! OmniInsert — mask-free video insertion of any reference -- 2025-10-14
- facebookresearch/DepthLM_Official -- 2025-10-14
- Built a 1288x RTFx Parakeet Speech-to-Text server... Enjoy! -- 2025-10-13
- Novel OpenGL Pixel Shader Dewarping -- 2025-10-13
- lovis93/next-scene-qwen-image-lora-2509 -- 2025-10-13
- Chinny (iOS/MacOS): offline, on-device voice cloning with an optimized Chatterbox model -- 2025-10-12
- herimor/voxtream -- 2025-10-12
- microsoft/VibeVoice-Large -- 2025-10-12
- chetwinlow1/Ovi -- 2025-10-12
- Phr00t/Qwen-Image-Edit-Rapid-AIO -- 2025-10-12
- NVlabs/rcm -- 2025-10-11
- Qwen3-VL-30B-A3B-Thinking GGUF with llama.cpp patch to run it -- 2025-10-10
- Does quantization need training data and will it lower performance for task outside of training data? -- 2025-10-10
- Qwen/Qwen3-VL-30B-A3B-Instruct -- 2025-10-10
- Project running VLMs on a Pi 5 and NV Jetson Orin Nano -- 2025-10-05
- Demo: I made an open-source version of Imagine by Claude (released yesterday) -- 2025-10-05
- nunchaku-tech/nunchaku-qwen-image-edit-2509 -- 2025-10-05
- cvlab-kaist/VIRAL -- 2025-10-05
- Tencent-Hunyuan/Hunyuan3D-Omni -- 2025-10-04
- tencent/HunyuanImage-3.0 -- 2025-10-04
- For llama.cpp/ggml AMD MI50s are now universally faster than NVIDIA P40s -- 2025-10-03
- MSI EdgeXpert Compact AI Supercomputer Based on NVIDIA DGX Spark -- 2025-10-03
- Kairos: Immutable Distro for K8s at the Edge -- 2025-10-03
- Nvidia Has Been Supplying NDA'ed Docs to Red Hat for Helping NVK Driver -- 2025-10-03
- Mini Laptop Needs Custom Kernel -- 2025-10-03
- jmanhype/vggt-mps -- 2025-10-02
- openbmb/VoxCPM-0.5B -- 2025-10-02
- Comfy-Org/Qwen-Image-Edit_ComfyUI -- 2025-10-02
- SOTA OCR on-device with Core ML and dots.ocr -- 2025-10-02
- Tencent-Hunyuan/SRPO -- 2025-09-30
- lodestones/Chroma1-Base -- 2025-09-30
- MV-RAG: Retrieval Augmented Multiview Diffusion -- 2025-09-30
- Phantom-video/HuMo -- 2025-09-27
- Build Your Own 6K Camera -- 2025-09-27
- Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer -- 2025-09-27
- OPPOer/Qwen-Image-Pruning -- 2025-09-27
- We made a new AI interface that is compatible with Ollama -- 2025-09-24
- if-ai/ComfyUI_HunyuanVideoFoley -- 2025-09-24
- Show HN: Inferencer – Run and deeply control local AI models (macOS release) -- 2025-09-24
- tencent/HunyuanWorld-Voyager -- 2025-09-24
- FireRedTeam/FireRedTTS2 -- 2025-09-24
- Wan-AI/Wan2.2-Animate-14B -- 2025-09-22
- decart-ai/Lucy-Edit-Dev -- 2025-09-22
- OpenBMB/VoxCPM -- 2025-09-22
- voicepowered-ai/VibeVoice-finetuning -- 2025-09-22
- alibaba-pai/Wan2.2-VACE-Fun-A14B -- 2025-09-21
- VideoGuard: Protecting Video Content from Unauthorized Editing -- 2025-09-21
- zli12321/Vision-SR1 -- 2025-09-19
- lrzjason/Comfyui-QwenEditUtils -- 2025-09-19
- Mini-o3/Mini-o3 -- 2025-09-19
- The AI-Scraping Free-for-All Is Coming to an End -- 2025-09-18
- Visible Watermarking with Gradio -- 2025-09-18
- Tencent-Hunyuan/HunyuanImage-2.1 -- 2025-09-17
- xiaomi-research/q-frame -- 2025-09-17
- TencentCloudADP/youtu-graphrag -- 2025-09-17
- Renting GPUs is hilariously cheap -- 2025-09-09
- Tencent-Hunyuan/HunyuanWorld-Voyager -- 2025-09-09
- Shipping textures as PNGs is suboptimal -- 2025-09-09
- LiquidAI/LFM2-VL-1.6B -- 2025-09-06
- A Training-Free, Task-Agnostic Framework for Enhancing MLLM Performance on High-Resolution Images -- 2025-09-06
- TencentARC/GenCompositor -- 2025-09-06
- TencentARC/ToonComposer -- 2025-09-04
- MeiGen-AI/InfiniteTalk -- 2025-09-04
- OWUI_File_Gen_Export v0.2.0 is out ! -- 2025-09-04
- MCP File Generation tool -- 2025-09-04
- tencent/Hunyuan-GameCraft-1.0 -- 2025-09-03
- InternVL 3.5 released : Best Open-Sourced Multi-Modal LLM, Ranks 3 overall -- 2025-08-31
- HunyuanVideo-Foley is out, an open source text-video-to-audio model -- 2025-08-31
- peteromallet/Flux-Kontext-InScene -- 2025-08-31
- TTS VibeVoice FastAPI -- 2025-08-30
- Microsoft VibeVoice TTS : Open-Sourced, Supports 90 minutes speech, 4 distinct speakers at a time -- 2025-08-29
- tencent/HunyuanVideo-Foley -- 2025-08-29
- bullerwins/Wan2.2-I2V-A14B-GGUF -- 2025-08-28
- QuantStack/Qwen-Image-Edit-GGUF -- 2025-08-28
- dvlab-research/MGM-Omni -- 2025-08-28
- RTX PRO 6000 MAX-Q Blackwell for LLM -- 2025-08-28
- Gemini 2.5 Flash Image -- 2025-08-27
- Arrexel/pattern-diffusion -- 2025-08-27
- An Alternative to Text-to-SQL -- 2025-08-25
- Best model for transcribing videos? -- 2025-08-25
- Compute Where It Counts: High Quality Sparsely Activated LLMs -- 2025-08-25
- moonshotai/Kimi-K2-Base -- 2025-08-25
- unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF -- 2025-08-25
- BlueLM-2.5-3B Technical Report -- 2025-08-25
- lightx2v/Qwen-Image-Lightning -- 2025-08-25
- Qwen-Image-Edit #6 overall on LMArena, best open model image editor -- 2025-08-24
- flybirdxx/ComfyUI-SDMatte -- 2025-08-24
- Wan-AI/Wan2.2-TI2V-5B -- 2025-08-24
- HiDream-ai/HiDream-E1-1 -- 2025-08-24
- We built a 12B model that beats Claude 4 Sonnet at video captioning while costing 17x less - fully open source -- 2025-08-15
- Francis-Rings/StableAvatar -- 2025-08-15
- SparcStation 1+ Finally Gets Attention -- 2025-08-15
- OmniSVG/OmniSVG -- 2025-08-15
- Phi-Ground Tech Report: Advancing Perception in GUI Grounding -- 2025-08-15
- NuMarkdown-8B-Thinking - first reasoning OCR VLM -- 2025-08-11
- Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling -- 2025-08-11
- Vision Language Model Alignment in TRL ⚡️ -- 2025-08-11
- Explore KittenTTS with Gradio: Easy Text-to-Speech model -- 2025-08-06
- [Editorial] AI personality -- 2025-08-05
- CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning -- 2025-08-05
- internlm/Intern-S1 -- 2025-08-05
- peteromallet/Flux-Kontext-InScene -- 2025-08-02
- A Dual-Screen Cyberdeck To Rule Them All -- 2025-08-02
- ziangcao0312/PhysX-3D -- 2025-07-29
- Playtron's Linux-Based GameOS Hits the Road with 1.0 -- 2025-07-26
- Remembering Chiptunes, the Demoscene and the Illegal Music of Keygens -- 2025-07-26
- albozes/shotbuddy -- 2025-07-25
- uttam-li/dfs -- 2025-07-25
- OmniSVG/OmniSVG -- 2025-07-25
- Freezer Monitoring: Because Ice Cream Is a Dish Best Served Cold -- 2025-07-25
- Fast LoRA inference for Flux with Diffusers and PEFT -- 2025-07-25
- boson-ai/higgs-audio -- 2025-07-24
- nvidia/canary-qwen-2.5b -- 2025-07-24
- TimeScope: How Long Can Your Video Large Multimodal Model Go? -- 2025-07-24
- THUDM/GLM-4.1V-Thinking -- 2025-07-23
- FunAudioLLM/ThinkSound -- 2025-07-23
- RaphaelLiu/PusaV1 -- 2025-07-23
- merve/smol-vision -- 2025-07-23
- Skywork/Skywork-R1V3-38B -- 2025-07-20
- ByteDance-Seed/Seed-X-PPO-7B -- 2025-07-20
- ChenDarYen/ComfyUI-NAG -- 2025-07-20
- Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation -- 2025-07-20
- Introcuding KokoroDoki a Local, Open-Source and Real-Time TTS. -- 2025-07-19
- Voxtral – Frontier open source speech understanding models -- 2025-07-19
- AI can now translate brain scans to text -- 2025-07-19
- quasiblob/ComfyUI-EsesImageEffectBloom -- 2025-07-18
- HiDream-ai/HiDream-E1-1 -- 2025-07-18
- Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective -- 2025-07-18
- runjiali-rl/vmem -- 2025-07-17
- Exploring State-Space-Model based Language Model in Music Generation -- 2025-07-16
- TextPixs: Glyph-Conditioned Diffusion with Character-Aware Attention and OCR-Guided Supervision -- 2025-07-15
- MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling -- 2025-07-14
- Need advice on how to improve Handwritten Text Recognition of names using Vision models (for academic research purposes) -- 2025-07-14
- DLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching -- 2025-07-08
- Efficient MultiModal Data Pipeline -- 2025-07-08
- black-forest-labs/FLUX.1-Kontext-dev-onnx -- 2025-07-07
- Subpixel Rendering For Impossibly Small Terminal Text -- 2025-07-04
- bytedance/ATI -- 2025-07-01
- AIDC-AI/Ovis-U1-3B -- 2025-07-01
- google/gemma-3n-E4B-it -- 2025-07-01
- baidu/ERNIE-4.5-21B-A3B-PT -- 2025-07-01
- THU-KEG/LongWriter-Zero-32B -- 2025-06-30
- Tencent-Hunyuan/Hunyuan3D-2.1 -- 2025-06-29
- bullerwins/FLUX.1-Kontext-dev-GGUF -- 2025-06-28
- google/gemma-3n-E2B-it -- 2025-06-28
- black-forest-labs/FLUX.1-Kontext-dev -- 2025-06-27
- 0.71-{\AA} resolution electron tomography enabled by deep learning aided information recovery -- 2025-06-26
- MeiGen-AI/MeiGen-MultiTalk -- 2025-06-26
- Tencent-Hunyuan/HunyuanPortrait -- 2025-06-24
- (0,2) hybrid models -- 2025-06-24
- 0-th Order Pseudo-differential Operator on the Circle -- 2025-06-24
- OmniGen2/OmniGen2 -- 2025-06-24
- gdhe17/Self-Forcing -- 2025-06-24
- Voyager: Real-Time Splatting City-Scale 3D Gaussians on Your Phone -- 2025-06-21
- lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill -- 2025-06-20
- Kijai/WanVideo_comfy -- 2025-06-20
- tencent/Hunyuan3D-2.1 -- 2025-06-20
- inclusionAI/Ming-Lite-Omni -- 2025-06-15
- New method for creating large 3D models of urban areas is faster and cheaper -- 2025-06-15
- vrgamedevgirl84/Wan14BT2VFusioniX -- 2025-06-13
- rusjoan/streamcrypt -- 2025-06-12
- tang-bd/fuse-dit -- 2025-06-12
- Show HN: 3DGS implementation in Nvidia Warp: clean, minimal, runs on CPU and GPU -- 2025-06-12
- 0.75 atoms improve the clock signal of 10,000 atoms -- 2025-06-12
- After Deepfaking YouTube, Google's Veo 3 Could Slop-Ify Video Games Next -- 2025-06-11
- manycore-research/SpatialLM -- 2025-06-09
- XiaomiMiMo/MiMo-VL-7B-RL -- 2025-06-09
- fishaudio/openaudio-s1-mini -- 2025-06-09
- rednote-hilab/dots.llm1.inst -- 2025-06-08
- tencent/HunyuanPortrait -- 2025-06-08
- Better quantization: Yet Another Quantization Algorithm -- 2025-06-08
- MCP server to connect LLM agents to any database -- 2025-06-08
- new gemma3 abliterated models from mlabonne -- 2025-06-08
- Sharing my a demo of tool for easy handwritten fine-tuning dataset creation! -- 2025-06-08
- Yess! Open-source strikes back! This is the closest I've seen anything come to competing with @GoogleDeepMind 's Veo 3 native audio and character motion. -- 2025-06-08
- For task-specific agents use task-specific LLMs for routing and hand off - NOT semantic techniques. -- 2025-06-08
- Face Age Prediction – Achieved Human-Level Accuracy (MAE ≈ 5) -- 2025-06-08
- Is there any open source project leveraging genAI to run quality checks on tabular data ? -- 2025-06-08
- Precomputing Transparency Order in 3D -- 2025-06-06
- nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1 -- 2025-06-05
- hexgrad/Kokoro-82M -- 2025-06-05
- Qwen/Qwen3-Embedding-0.6B-GGUF -- 2025-06-05
- AMAP-ML/UniVG-R1 -- 2025-06-02
- showlab/OmniConsistency -- 2025-06-02
- tencent/HunyuanVideo-Avatar -- 2025-06-02
- Datadog/Toto-Open-Base-1.0 -- 2025-06-01
- facebook/KernelLLM -- 2025-05-31
- 0.08 fF, 0.72 nA dark current, 91% Quantum Efficiency, 38 Gb/s Nano-photodetector on a 45 nm CMOS Silicon-Photonic Platform -- 2025-05-30
- 1000 FPS HDR Video With a Spike-RGB Hybrid Camera -- 2025-05-30