The Curious Engineer

All blogs / AI / ML

fal.ai Blog

blog.fal.ai

Latest generative AI model releases and tutorials. FLUX updates, video AI breakthroughs, developer guides, and industry insights from fal.ai.

AI / MLPerformance / optimization

’23’24’25’26
Posts
122 from 30 Mar 2023 to 20 Oct 2026
Posting
weekly (39 in the last year)
Kind
company blog
Feed
https://blog.fal.ai/rss/

2026 23

  1. EAGLE-4 Technical Deepdive
  2. H3 Max: Built with fal Inference and Training
  3. Introducing H3 Max by fal
  4. From clay 3d render to a real action short: a 3D-to-AI pipeline with total control
  5. FASHN AI: reimagining fashion and photography
  6. Serving sub-second Ideogram v4 without quality loss
  7. How We Achieved ~1000 tok/s and 16x Throughput with DSpark for Ideogram V4 Prompt Expander
  8. The operational reality of marketing inside an AI company
  9. fal and AWS: Building for the Next Phase of Generative Media
  10. Building long-term trust in a world where creation moves at the speed of thought
  11. Introducing PATINA
  12. Inworld TTS-1.5 Max Now Available on fal
  13. Connect your AI to 1,000+ models with the fal MCP Server
  14. HeyGen models are now available on fal
  15. Seedream 5.0 Lite Prompting Guide
  16. Ulysses Unbound: Experiments in Communication–Computation Overlap
  17. Instruction-level control with Inline Elementwise ASM in Triton
  18. Kling 3.0 Prompting Guide
  19. Kling 3.0 is Now Available on fal
  20. Crafting Efficient Kernels with Epilogue Fusion
  21. Grok Imagine is Now Available on fal
  22. Chasing 6+ TB/s: an MXFP8 quantizer on Blackwell
  23. LTX 2.0 is Now Available on fal

2025 80

  1. Chatterbox Turbo is now available on fal
  2. Our Series D: Scaling fal
  3. Pika API is now powered by fal
  4. Kling 2.6 is Now Available on fal
  5. Seedream 4.5 is Now Available on fal
  6. Introducing Kling O1 Video Available Exclusively as an API on fal
  7. Training FLUX.2 LoRAs
  8. FLUX.2 Is Now Available on fal
  9. ImagineArt 1.5 Is Now Live on fal
  10. NanoBanana Pro Is Now available on fal
  11. Comparing the Best AI Upscalers for Video and Images
  12. Key Takeaways from the First Generative Media Conference
  13. Welcoming the Remade Team to fal
  14. Sora 2 & GPT Image 1 are now available on fal
  15. Google Veo 3.1 vs 3.0: Worth the Upgrade? | fal.ai blog
  16. Sima Upscaler Is Live on fal!
  17. Introducing FIBO: Structured Control for Text-to-Image Generation
  18. MiniMax Hailuo 2.3 is now available on fal
  19. Introducing FlashPack: Lightning-Fast Model Loading for PyTorch
  20. LTX 2.0 is Now Available on fal
  21. Kling 2.5 Turbo Standard is now available on fal
  22. Beatoven.ai’s maestro model is now live on fal
  23. Reve is now available on fal
  24. Meshy is Now Available on fal
  25. VEO 3.1 is now available on fal
  26. Introducing Moondream 3 Preview on fal
  27. Ovi is Now Available on fal
  28. fal is now available through Google Cloud Marketplace
  29. Hunyuan Image 3.0 is now available on fal
  30. VEED Fabric 1.0 on fal: Turn Any Image Into a Talking Video
  31. Wan 2.5 Preview is now available on fal
  32. KLING 2.5 Turbo Pro is Now Available on fal
  33. Isaac 0.1: the First Perceptive-language Model on fal
  34. Seedream 4.0 on fal: Fast, Consistent, 4K-Ready Image Creation
  35. Stable Audio 2.5 Now Available on fal
  36. AI Where Creation Happens: fal x IMG.LY
  37. Sonauto Now Available on fal
  38. Introducing Gemini 2.5 Flash Image Edit aka "nano-banana"
  39. Mirelo SFX Now Available on fal
  40. Introducing Qwen Image Edit
  41. Powering Creative Workflows with Weavy x fal
  42. Introducing Qwen Image
  43. Moonvalley's Marey Realism v1.5 is now on fal - The most advanced generative filmmaking yet.
  44. Introducing Wan 2.2 14b Text to Image
  45. Introducing Ideogram Character
  46. Introducing the Flux.1 Krea [dev] On fal
  47. fal is Generative Media - Our $125M Series C
  48. WAN 2.2 vs WAN 2.1: What's New and How to Upgrade Your Video Pipeline
  49. WAN 2.2 API: Complete Developer Guide to Next-Generation Video Synthesis
  50. Bria’s 3.2 Text-to-Image and Video Background Removal Now on fal
  51. New LTXV 0.9.8 Model Live on fal
  52. Announcing FLUX.1 Kontext [dev] Inference & Training
  53. VEED Now Available on fal
  54. Veo 3 is now available at fal
  55. Resemble Now Available on fal
  56. FLUX.1 Kontext Image Editing Models are now available at fal
  57. PixVerse v4.5 Now Available on fal
  58. Hummingbird-0 AI Lip Sync Model by Tavus now available on fal
  59. FASHN Try-On v1.5 Available on fal
  60. Kling 2.0: Available Only on fal
  61. New Finegrain Models Live on fal
  62. Sync Labs' Lipsync 2.0 Model Now Available on fal
  63. MiniMax Text-to-Speech Models now available on fal
  64. CassetteAI Music Generator Model now available on fal
  65. Announcing fal Models Availability in Adobe’s Ecosystem
  66. Launch of fal AI integration on Vercel
  67. Pika Models Now Available on fal
  68. Topaz Video AI Upscaler now live on fal
  69. Vidu 2.0 Models Live on fal
  70. Veo2 Image-to-Video now available on fal
  71. New Image Editing Model from Easel AI Now Available on fal
  72. New LTX Video Model Live on fal
  73. Juggernaut FLUX Series: Redefining Photorealism
  74. ElevenLabs Audio Suite: Next-Generation Voice and Audio AI Now on fal
  75. New BRIA AI Image and Editing Models Live on fal
  76. Mastering Video Generation with Veo 2: A Comprehensive Guide
  77. Veo2: State-of-the-Art Video Generation Now on fal
  78. fal Raises $49M Series B to Power the Future of AI Video
  79. Introducing the AI Video Developer Starter Kit
  80. Introducing PlayDialog: The Next Evolution in Conversational AI

2024 15

  1. Introducing MiniMax (Hailuo) video-01-Live: Transform Static Art into Dynamic Materpieces
  2. New SOTA Virtual Try-On Model by FASHN live on fal
  3. Introducing the FLUX Portrait Trainer
  4. Announcing red_panda by Recraft
  5. Announcing Stable Diffusion 3.5 Large & Turbo by stability.ai
  6. Training FLUX Style LoRA on fal
  7. Announcing FLUX1.1 [pro] by BFL and FLUX [dev] speed improvements
  8. Generative media needs speed. fal has raised $23M to accelerate.
  9. Announcing Flux by Black Forest Labs: The Next Leap in Text-to-Image Models
  10. AuraSR V2
  11. Introducing AuraFlow v0.1, an Open Exploration of Large Rectified Flow Models
  12. Introducing AuraSR - An open reproduction of the GigaGAN Upscaler
  13. fal News: Stable Diffusion 3 available now, ComfyUI workflows and more
  14. Introducing On-demand Preference Fine-Tuning for Image Models
  15. fal - Vercel Integration

2023 4

  1. Building Applications with Real-Time Stable Diffusion APIs
  2. Introducing fal Model Endpoints
  3. Accelerate Hyperparameter Tuning with fal
  4. Introducing fal