Image & Video Generation

Diffusion models, Stable Diffusion, ComfyUI, text-to-image/video

272 articles across 100 editions

Articles

  1. Ling-2.5-1T: 1T Parameter Open-Source Instant Model with 1M Context -- 2026-02-16
  2. Qwen3.5-397B-A17B Unsloth GGUFs — Run on Consumer Hardware -- 2026-02-16
  3. Running Qwen3-Coder-Next 80B on 8GB VRAM — 300x Speedup via Custom Expert Caching -- 2026-02-16
  4. Flame Graphs vs Tree Maps vs Sunburst (2017) -- 2025-12-31
  5. 39C3: Recreating Sandstorm -- 2025-12-31
  6. EditMGT — fast, localized image editing with Masked Generative Transformers -- 2025-12-30
  7. Francis-Rings/FlashPortrait -- 2025-12-30
  8. zai-org/GLM-TTS -- 2025-12-30
  9. Flowception: Temporally Expansive Flow Matching for Video Generation -- 2025-12-30
  10. Key Highlights of NVIDIA’s New Model: Nemotron 3 -- 2025-12-17
  11. The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator -- 2025-12-17
  12. ostris/Z-Image-De-Turbo -- 2025-12-12
  13. zai-org/GLM-TTS -- 2025-12-11
  14. openbmb/VoxCPM1.5 -- 2025-12-11
  15. ByteDance-Seed/Depth-Anything-3 -- 2025-12-10
  16. seominseok0429/Upsample-Anything-A-Simple-and-Hard-to-Beat-Baseline-for-Feature-Upsampling -- 2025-12-09
  17. lrzjason/QwenEdit-Anything2Real_Alpha -- 2025-12-08
  18. How Big is Your Video Again? Square vs Rectangular Pixels -- 2025-12-08
  19. shubh-io/DockMate -- 2025-12-08
  20. Comfy-Org/HunyuanVideo_1.5_repackaged -- 2025-12-08
  21. ByteDance/BindWeave -- 2025-12-08
  22. apple/starflow -- 2025-12-04
  23. princepainter/ComfyUI-PainterLongVideo -- 2025-12-04
  24. OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing -- 2025-12-03
  25. Z-Image: Powerful and highly efficient image generation model with 6B parameters -- 2025-12-03
  26. FLUX.2: Frontier Visual Intelligence -- 2025-11-28
  27. Diffusers welcomes FLUX-2 -- 2025-11-26
  28. dx8152/Relight -- 2025-11-26
  29. Question About Motherboards -- 2025-11-26
  30. Qwen/Qwen3-VL-4B-Instruct -- 2025-11-20
  31. Soul-AILab/SoulX-Podcast-1.7B -- 2025-11-20
  32. wildminder/ComfyUI-DyPE -- 2025-11-19
  33. lightx2v/Autoencoders -- 2025-11-19
  34. We ran over 600 image generations to compare AI image models -- 2025-11-13
  35. dx8152/Qwen-Image-Edit-2509-Relight -- 2025-11-13
  36. meituan-longcat/LongCat-Video -- 2025-11-05
  37. allenai/olmOCR-2-7B-1025-FP8 -- 2025-11-05
  38. deepseek-ai/DeepSeek-OCR -- 2025-11-04
  39. LiquidAI/LFM2-VL-3B -- 2025-11-04
  40. Qwen/Qwen3-VL-235B-A22B-Thinking -- 2025-11-04
  41. DeepSeek may have found a new way to improve AI’s ability to remember -- 2025-11-02
  42. Qwen/Qwen3-VL-8B-Thinking -- 2025-11-02
  43. nvidia/omnivinci -- 2025-11-02
  44. OpenImagingLab/FlashVSR -- 2025-11-02
  45. Build Your Own Force-Feedback Joystick -- 2025-11-02
  46. ZOZO's Contact Solver for physics-based simulations -- 2025-11-01
  47. valiantcat/Qwen-Image-Edit-MeiTu -- 2025-11-01
  48. ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing -- 2025-11-01
  49. fireleyfreya/AI-Art-Generator -- 2025-10-30
  50. krea/krea-realtime-video -- 2025-10-30
  51. Cerebras REAP'd GLM4.6: 25%, 30%, 40% pruned FP8 checkpoints on HF! -- 2025-10-28
  52. Qwen/Qwen3-VL-30B-A3B-Instruct-FP8 -- 2025-10-28
  53. lightx2v/Wan2.2-Distill-Loras -- 2025-10-28
  54. GPT-OSS-20b TAKE THE HELM! Further experiments in autopilot. -- 2025-10-28
  55. 5060ti chads... ram overclocking, the phantom menace -- 2025-10-28
  56. Batch inference locally on 4080 -- 2025-10-28
  57. 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
  58. Pico Banana: Large-Scale Dataset for Image Editing by Apple -- 2025-10-27
  59. dvlab-research/DreamOmni2 -- 2025-10-25
  60. bytetriper/RAE -- 2025-10-25
  61. tencent/POINTS-Reader -- 2025-10-25
  62. Stitch: Training-Free Position Control in Multimodal Diffusion Transformers -- 2025-10-25
  63. Llama.cpp is looking for M5 Neural Accelerator performance testers -- 2025-10-24
  64. NVIDIA sent me a 5090 so I can demo Qwen3-VL GGUF -- 2025-10-24
  65. AMD ROCm 7.9 and dwindling GPU support -- 2025-10-24
  66. Show HN: Cuq – Formal Verification of Rust GPU Kernels -- 2025-10-24
  67. [Editorial] https://github.com/DrewThomasson/ebook2audiobook -- 2025-10-23
  68. [Editorial] https://github.com/lfnovo/open-notebook -- 2025-10-23
  69. tencent/Hunyuan3D-Omni -- 2025-10-23
  70. Doby-Xu/WithAnyone -- 2025-10-22
  71. lightx2v/Wan2.2-I2V-A14B-Moe-Distill-Lightx2v -- 2025-10-22
  72. mit-han-lab/streaming-vlm -- 2025-10-22
  73. tencent-ailab/SongPrep -- 2025-10-20
  74. opendatalab/MinerU2.5-2509-1.2B -- 2025-10-20
  75. QuantStack/Qwen-Image-Edit-2509-GGUF -- 2025-10-20
  76. LM Studio and VL models -- 2025-10-19
  77. Qwen/Qwen-Image-Edit-2509 -- 2025-10-19
  78. Alpha-VLLM/Lumina-DiMOO -- 2025-10-19
  79. linkedlist771/SoraWatermarkCleaner -- 2025-10-19
  80. Audio transcription with llama.cpp multimodal -- 2025-10-18
  81. I built a fully automated AI podcast generator that connects to ollama -- 2025-10-18
  82. Paper2Video — turn a research paper into a full presentation video (slides, speech, talking head) -- 2025-10-15
  83. Practical OCR with Nanonets OCR2‑3B -- 2025-10-15
  84. neuphonic/neutts-air -- 2025-10-15
  85. Qwen/Qwen3-VL-235B-A22B-Instruct -- 2025-10-15
  86. XiaomiMiMo/MiMo-Audio-Eval -- 2025-10-15
  87. Very interesting! OmniInsert — mask-free video insertion of any reference -- 2025-10-14
  88. facebookresearch/DepthLM_Official -- 2025-10-14
  89. Built a 1288x RTFx Parakeet Speech-to-Text server... Enjoy! -- 2025-10-13
  90. Novel OpenGL Pixel Shader Dewarping -- 2025-10-13
  91. lovis93/next-scene-qwen-image-lora-2509 -- 2025-10-13
  92. Chinny (iOS/MacOS): offline, on-device voice cloning with an optimized Chatterbox model -- 2025-10-12
  93. herimor/voxtream -- 2025-10-12
  94. microsoft/VibeVoice-Large -- 2025-10-12
  95. chetwinlow1/Ovi -- 2025-10-12
  96. Phr00t/Qwen-Image-Edit-Rapid-AIO -- 2025-10-12
  97. NVlabs/rcm -- 2025-10-11
  98. Qwen3-VL-30B-A3B-Thinking GGUF with llama.cpp patch to run it -- 2025-10-10
  99. Does quantization need training data and will it lower performance for task outside of training data? -- 2025-10-10
  100. Qwen/Qwen3-VL-30B-A3B-Instruct -- 2025-10-10
  101. Project running VLMs on a Pi 5 and NV Jetson Orin Nano -- 2025-10-05
  102. Demo: I made an open-source version of Imagine by Claude (released yesterday) -- 2025-10-05
  103. nunchaku-tech/nunchaku-qwen-image-edit-2509 -- 2025-10-05
  104. cvlab-kaist/VIRAL -- 2025-10-05
  105. Tencent-Hunyuan/Hunyuan3D-Omni -- 2025-10-04
  106. tencent/HunyuanImage-3.0 -- 2025-10-04
  107. For llama.cpp/ggml AMD MI50s are now universally faster than NVIDIA P40s -- 2025-10-03
  108. MSI EdgeXpert Compact AI Supercomputer Based on NVIDIA DGX Spark -- 2025-10-03
  109. Kairos: Immutable Distro for K8s at the Edge -- 2025-10-03
  110. Nvidia Has Been Supplying NDA'ed Docs to Red Hat for Helping NVK Driver -- 2025-10-03
  111. Mini Laptop Needs Custom Kernel -- 2025-10-03
  112. jmanhype/vggt-mps -- 2025-10-02
  113. openbmb/VoxCPM-0.5B -- 2025-10-02
  114. Comfy-Org/Qwen-Image-Edit_ComfyUI -- 2025-10-02
  115. SOTA OCR on-device with Core ML and dots.ocr -- 2025-10-02
  116. Tencent-Hunyuan/SRPO -- 2025-09-30
  117. lodestones/Chroma1-Base -- 2025-09-30
  118. MV-RAG: Retrieval Augmented Multiview Diffusion -- 2025-09-30
  119. Phantom-video/HuMo -- 2025-09-27
  120. Build Your Own 6K Camera -- 2025-09-27
  121. Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer -- 2025-09-27
  122. OPPOer/Qwen-Image-Pruning -- 2025-09-27
  123. We made a new AI interface that is compatible with Ollama -- 2025-09-24
  124. if-ai/ComfyUI_HunyuanVideoFoley -- 2025-09-24
  125. Show HN: Inferencer – Run and deeply control local AI models (macOS release) -- 2025-09-24
  126. tencent/HunyuanWorld-Voyager -- 2025-09-24
  127. FireRedTeam/FireRedTTS2 -- 2025-09-24
  128. Wan-AI/Wan2.2-Animate-14B -- 2025-09-22
  129. decart-ai/Lucy-Edit-Dev -- 2025-09-22
  130. OpenBMB/VoxCPM -- 2025-09-22
  131. voicepowered-ai/VibeVoice-finetuning -- 2025-09-22
  132. alibaba-pai/Wan2.2-VACE-Fun-A14B -- 2025-09-21
  133. VideoGuard: Protecting Video Content from Unauthorized Editing -- 2025-09-21
  134. zli12321/Vision-SR1 -- 2025-09-19
  135. lrzjason/Comfyui-QwenEditUtils -- 2025-09-19
  136. Mini-o3/Mini-o3 -- 2025-09-19
  137. The AI-Scraping Free-for-All Is Coming to an End -- 2025-09-18
  138. Visible Watermarking with Gradio -- 2025-09-18
  139. Tencent-Hunyuan/HunyuanImage-2.1 -- 2025-09-17
  140. xiaomi-research/q-frame -- 2025-09-17
  141. TencentCloudADP/youtu-graphrag -- 2025-09-17
  142. Renting GPUs is hilariously cheap -- 2025-09-09
  143. Tencent-Hunyuan/HunyuanWorld-Voyager -- 2025-09-09
  144. Shipping textures as PNGs is suboptimal -- 2025-09-09
  145. LiquidAI/LFM2-VL-1.6B -- 2025-09-06
  146. A Training-Free, Task-Agnostic Framework for Enhancing MLLM Performance on High-Resolution Images -- 2025-09-06
  147. TencentARC/GenCompositor -- 2025-09-06
  148. TencentARC/ToonComposer -- 2025-09-04
  149. MeiGen-AI/InfiniteTalk -- 2025-09-04
  150. OWUI_File_Gen_Export v0.2.0 is out ! -- 2025-09-04
  151. MCP File Generation tool -- 2025-09-04
  152. tencent/Hunyuan-GameCraft-1.0 -- 2025-09-03
  153. InternVL 3.5 released : Best Open-Sourced Multi-Modal LLM, Ranks 3 overall -- 2025-08-31
  154. HunyuanVideo-Foley is out, an open source text-video-to-audio model -- 2025-08-31
  155. peteromallet/Flux-Kontext-InScene -- 2025-08-31
  156. TTS VibeVoice FastAPI -- 2025-08-30
  157. Microsoft VibeVoice TTS : Open-Sourced, Supports 90 minutes speech, 4 distinct speakers at a time -- 2025-08-29
  158. tencent/HunyuanVideo-Foley -- 2025-08-29
  159. bullerwins/Wan2.2-I2V-A14B-GGUF -- 2025-08-28
  160. QuantStack/Qwen-Image-Edit-GGUF -- 2025-08-28
  161. dvlab-research/MGM-Omni -- 2025-08-28
  162. RTX PRO 6000 MAX-Q Blackwell for LLM -- 2025-08-28
  163. Gemini 2.5 Flash Image -- 2025-08-27
  164. Arrexel/pattern-diffusion -- 2025-08-27
  165. An Alternative to Text-to-SQL -- 2025-08-25
  166. Best model for transcribing videos? -- 2025-08-25
  167. Compute Where It Counts: High Quality Sparsely Activated LLMs -- 2025-08-25
  168. moonshotai/Kimi-K2-Base -- 2025-08-25
  169. unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF -- 2025-08-25
  170. BlueLM-2.5-3B Technical Report -- 2025-08-25
  171. lightx2v/Qwen-Image-Lightning -- 2025-08-25
  172. Qwen-Image-Edit #6 overall on LMArena, best open model image editor -- 2025-08-24
  173. flybirdxx/ComfyUI-SDMatte -- 2025-08-24
  174. Wan-AI/Wan2.2-TI2V-5B -- 2025-08-24
  175. HiDream-ai/HiDream-E1-1 -- 2025-08-24
  176. We built a 12B model that beats Claude 4 Sonnet at video captioning while costing 17x less - fully open source -- 2025-08-15
  177. Francis-Rings/StableAvatar -- 2025-08-15
  178. SparcStation 1+ Finally Gets Attention -- 2025-08-15
  179. OmniSVG/OmniSVG -- 2025-08-15
  180. Phi-Ground Tech Report: Advancing Perception in GUI Grounding -- 2025-08-15
  181. NuMarkdown-8B-Thinking - first reasoning OCR VLM -- 2025-08-11
  182. Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling -- 2025-08-11
  183. Vision Language Model Alignment in TRL ⚡️ -- 2025-08-11
  184. Explore KittenTTS with Gradio: Easy Text-to-Speech model -- 2025-08-06
  185. [Editorial] AI personality -- 2025-08-05
  186. CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning -- 2025-08-05
  187. internlm/Intern-S1 -- 2025-08-05
  188. peteromallet/Flux-Kontext-InScene -- 2025-08-02
  189. A Dual-Screen Cyberdeck To Rule Them All -- 2025-08-02
  190. ziangcao0312/PhysX-3D -- 2025-07-29
  191. Playtron's Linux-Based GameOS Hits the Road with 1.0 -- 2025-07-26
  192. Remembering Chiptunes, the Demoscene and the Illegal Music of Keygens -- 2025-07-26
  193. albozes/shotbuddy -- 2025-07-25
  194. uttam-li/dfs -- 2025-07-25
  195. OmniSVG/OmniSVG -- 2025-07-25
  196. Freezer Monitoring: Because Ice Cream Is a Dish Best Served Cold -- 2025-07-25
  197. Fast LoRA inference for Flux with Diffusers and PEFT -- 2025-07-25
  198. boson-ai/higgs-audio -- 2025-07-24
  199. nvidia/canary-qwen-2.5b -- 2025-07-24
  200. TimeScope: How Long Can Your Video Large Multimodal Model Go? -- 2025-07-24
  201. THUDM/GLM-4.1V-Thinking -- 2025-07-23
  202. FunAudioLLM/ThinkSound -- 2025-07-23
  203. RaphaelLiu/PusaV1 -- 2025-07-23
  204. merve/smol-vision -- 2025-07-23
  205. Skywork/Skywork-R1V3-38B -- 2025-07-20
  206. ByteDance-Seed/Seed-X-PPO-7B -- 2025-07-20
  207. ChenDarYen/ComfyUI-NAG -- 2025-07-20
  208. Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation -- 2025-07-20
  209. Introcuding KokoroDoki a Local, Open-Source and Real-Time TTS. -- 2025-07-19
  210. Voxtral – Frontier open source speech understanding models -- 2025-07-19
  211. AI can now translate brain scans to text -- 2025-07-19
  212. quasiblob/ComfyUI-EsesImageEffectBloom -- 2025-07-18
  213. HiDream-ai/HiDream-E1-1 -- 2025-07-18
  214. Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective -- 2025-07-18
  215. runjiali-rl/vmem -- 2025-07-17
  216. Exploring State-Space-Model based Language Model in Music Generation -- 2025-07-16
  217. TextPixs: Glyph-Conditioned Diffusion with Character-Aware Attention and OCR-Guided Supervision -- 2025-07-15
  218. MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling -- 2025-07-14
  219. Need advice on how to improve Handwritten Text Recognition of names using Vision models (for academic research purposes) -- 2025-07-14
  220. DLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching -- 2025-07-08
  221. Efficient MultiModal Data Pipeline -- 2025-07-08
  222. black-forest-labs/FLUX.1-Kontext-dev-onnx -- 2025-07-07
  223. Subpixel Rendering For Impossibly Small Terminal Text -- 2025-07-04
  224. bytedance/ATI -- 2025-07-01
  225. AIDC-AI/Ovis-U1-3B -- 2025-07-01
  226. google/gemma-3n-E4B-it -- 2025-07-01
  227. baidu/ERNIE-4.5-21B-A3B-PT -- 2025-07-01
  228. THU-KEG/LongWriter-Zero-32B -- 2025-06-30
  229. Tencent-Hunyuan/Hunyuan3D-2.1 -- 2025-06-29
  230. bullerwins/FLUX.1-Kontext-dev-GGUF -- 2025-06-28
  231. google/gemma-3n-E2B-it -- 2025-06-28
  232. black-forest-labs/FLUX.1-Kontext-dev -- 2025-06-27
  233. 0.71-{\AA} resolution electron tomography enabled by deep learning aided information recovery -- 2025-06-26
  234. MeiGen-AI/MeiGen-MultiTalk -- 2025-06-26
  235. Tencent-Hunyuan/HunyuanPortrait -- 2025-06-24
  236. (0,2) hybrid models -- 2025-06-24
  237. 0-th Order Pseudo-differential Operator on the Circle -- 2025-06-24
  238. OmniGen2/OmniGen2 -- 2025-06-24
  239. gdhe17/Self-Forcing -- 2025-06-24
  240. Voyager: Real-Time Splatting City-Scale 3D Gaussians on Your Phone -- 2025-06-21
  241. lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill -- 2025-06-20
  242. Kijai/WanVideo_comfy -- 2025-06-20
  243. tencent/Hunyuan3D-2.1 -- 2025-06-20
  244. inclusionAI/Ming-Lite-Omni -- 2025-06-15
  245. New method for creating large 3D models of urban areas is faster and cheaper -- 2025-06-15
  246. vrgamedevgirl84/Wan14BT2VFusioniX -- 2025-06-13
  247. rusjoan/streamcrypt -- 2025-06-12
  248. tang-bd/fuse-dit -- 2025-06-12
  249. Show HN: 3DGS implementation in Nvidia Warp: clean, minimal, runs on CPU and GPU -- 2025-06-12
  250. 0.75 atoms improve the clock signal of 10,000 atoms -- 2025-06-12
  251. After Deepfaking YouTube, Google's Veo 3 Could Slop-Ify Video Games Next -- 2025-06-11
  252. manycore-research/SpatialLM -- 2025-06-09
  253. XiaomiMiMo/MiMo-VL-7B-RL -- 2025-06-09
  254. fishaudio/openaudio-s1-mini -- 2025-06-09
  255. rednote-hilab/dots.llm1.inst -- 2025-06-08
  256. tencent/HunyuanPortrait -- 2025-06-08
  257. Better quantization: Yet Another Quantization Algorithm -- 2025-06-08
  258. MCP server to connect LLM agents to any database -- 2025-06-08
  259. new gemma3 abliterated models from mlabonne -- 2025-06-08
  260. Sharing my a demo of tool for easy handwritten fine-tuning dataset creation! -- 2025-06-08
  261. 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
  262. For task-specific agents use task-specific LLMs for routing and hand off - NOT semantic techniques. -- 2025-06-08
  263. Face Age Prediction – Achieved Human-Level Accuracy (MAE ≈ 5) -- 2025-06-08
  264. Is there any open source project leveraging genAI to run quality checks on tabular data ? -- 2025-06-08
  265. Precomputing Transparency Order in 3D -- 2025-06-06
  266. nvidia/Llama-3.1-Nemotron-Nano-VL-8B-V1 -- 2025-06-05
  267. hexgrad/Kokoro-82M -- 2025-06-05
  268. Qwen/Qwen3-Embedding-0.6B-GGUF -- 2025-06-05
  269. AMAP-ML/UniVG-R1 -- 2025-06-02
  270. showlab/OmniConsistency -- 2025-06-02
  271. tencent/HunyuanVideo-Avatar -- 2025-06-02
  272. Datadog/Toto-Open-Base-1.0 -- 2025-06-01
  273. facebook/KernelLLM -- 2025-05-31
  274. 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
  275. 1000 FPS HDR Video With a Spike-RGB Hybrid Camera -- 2025-05-30