https://ai-fieldnotes.com/model-drops/ New AI video, image, audio and language model releases, one dated line each, linked to the maker. Links only. en-gb Mon, 19 Oct 2026 12:00:00 GMT https://ai-fieldnotes.com/model-drops/#2026-10-19-minimax-minimax-m3-1-flash https://ai-fieldnotes.com/model-drops/#2026-10-19-minimax-minimax-m3-1-flash Mon, 19 Oct 2026 12:00:00 GMT Credit: MiniMax. New Flash language model for agents and coding; MiniMax says nearly three times faster online and 70% cheaper to use. Source: https://www.minimax.io/blog/minimax-m31f https://ai-fieldnotes.com/model-drops/#2026-10-17-deepseek-deepseek-v4-1-flash-1017 https://ai-fieldnotes.com/model-drops/#2026-10-17-deepseek-deepseek-v4-1-flash-1017 Sat, 17 Oct 2026 12:00:00 GMT Credit: DeepSeek. V4.1 Flash updated to version 1017, now behind the deepseek-flash API name, with weights on Hugging Face. Source: https://www.deepseek.com/en/news/deepseek-v4-1-flash/ https://ai-fieldnotes.com/model-drops/#2026-10-15-black-forest-labs-flux-3-image-klein https://ai-fieldnotes.com/model-drops/#2026-10-15-black-forest-labs-flux-3-image-klein Thu, 15 Oct 2026 12:00:00 GMT Credit: Black Forest Labs. 5.6B open-weights image model for text-to-image, editing and multi-reference with up to 10 images, native 4K. For film: Runs locally on consumer GPUs, and bounding boxes place elements where you ask. Source: https://bfl.ai/blog/flux-3-image-klein https://ai-fieldnotes.com/model-drops/#2026-10-15-bytedance-byteplus-omnihuman-2-0 https://ai-fieldnotes.com/model-drops/#2026-10-15-bytedance-byteplus-omnihuman-2-0 Thu, 15 Oct 2026 12:00:00 GMT Credit: ByteDance (BytePlus). Audio-driven avatar video from one image plus speech, music or dialogue, now on the BytePlus API. For film: Lip movement and expression follow the audio, for talking and singing characters. Source: https://www.byteplus.com/en/product/omnihuman https://ai-fieldnotes.com/model-drops/#2026-10-15-elevenlabs-instant-soundtracks https://ai-fieldnotes.com/model-drops/#2026-10-15-elevenlabs-instant-soundtracks Thu, 15 Oct 2026 12:00:00 GMT Credit: ElevenLabs. Upload a video and get an original score plus sound effects placed on the timeline, in ElevenCreative and the API. For film: Effects come as separate layers you can retime; the score can follow existing audio. Source: https://elevenlabs.io/blog/introducing-instant-soundtracks https://ai-fieldnotes.com/model-drops/#2026-10-15-krea-krea-3 https://ai-fieldnotes.com/model-drops/#2026-10-15-krea-krea-3 Thu, 15 Oct 2026 12:00:00 GMT Credit: Krea. Krea's new image editing model: most edits under 8 seconds at native 2K, up to 6 reference images per edit. For film: Keeps the same character across poses, locations and light for a consistent set. Source: https://www.krea.ai/blog/introducing-krea-3 https://ai-fieldnotes.com/model-drops/#2026-10-15-kuaishou-kling-4-0 https://ai-fieldnotes.com/model-drops/#2026-10-15-kuaishou-kling-4-0 Thu, 15 Oct 2026 12:00:00 GMT Credit: Kuaishou. Kling 4.0 fully live on the Kling site: native 30-second takes, Omni Reference with up to 15 references and 10 keyframes. For film: One-pass long takes and keyframe control for continuous scenes; API access is promised soon. Source: https://kling.ai/release-note/release-history https://ai-fieldnotes.com/model-drops/#2026-10-15-meta-muse-spark-open https://ai-fieldnotes.com/model-drops/#2026-10-15-meta-muse-spark-open Thu, 15 Oct 2026 12:00:00 GMT Credit: Meta. Open-weight multimodal model, 816B total and 42B active, 1M-token context, built for coding and agentic work. Source: https://research.meta.ai/blog/muse-spark-open https://ai-fieldnotes.com/model-drops/#2026-10-14-heygen-heygen-voice https://ai-fieldnotes.com/model-drops/#2026-10-14-heygen-heygen-voice Wed, 14 Oct 2026 12:00:00 GMT Credit: HeyGen. Voice cloning that turns a recording, a script and a target image into speech shaped for the scene on screen. For film: Delivery and room acoustics match the shot, from studio to street to a moving car. Source: https://www.heygen.com/research/heygen-voice-scene-aware-voice-cloning https://ai-fieldnotes.com/model-drops/#2026-10-14-mirelo-mirelo-sfx-2-0 https://ai-fieldnotes.com/model-drops/#2026-10-14-mirelo-mirelo-sfx-2-0 Wed, 14 Oct 2026 12:00:00 GMT Credit: Mirelo. Video-to-sound model that replaces a clip's audio with synced effects, foley and ambience while keeping dialogue. For film: Keeps dialogue while adding sound; Studio and API take clips up to 10 minutes. Source: https://mirelo.ai/blog/mirelo-sfx-2-0 https://ai-fieldnotes.com/model-drops/#2026-10-13-fish-audio-drama-3 https://ai-fieldnotes.com/model-drops/#2026-10-13-fish-audio-drama-3 Tue, 13 Oct 2026 12:00:00 GMT Credit: Fish Audio. Fish Audio's most emotive text-to-speech model, live on fish.audio, the Fish Audio app and the API. For film: Follows direction: a whisper stays a whisper and a laugh lands where you put it. Source: https://fish.audio/blog/fish-audio-drama-3/ https://ai-fieldnotes.com/model-drops/#2026-10-13-google-gemini-4-argon https://ai-fieldnotes.com/model-drops/#2026-10-13-google-gemini-4-argon Tue, 13 Oct 2026 12:00:00 GMT Credit: Google. Google's frontier model now generally available in the Gemini API, AI Studio and the Gemini app for Pro and Ultra. Source: https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-argon/ https://ai-fieldnotes.com/model-drops/#2026-10-11-alibaba-wan-3-0-prime https://ai-fieldnotes.com/model-drops/#2026-10-11-alibaba-wan-3-0-prime Sun, 11 Oct 2026 12:00:00 GMT Credit: Alibaba. Faster Wan 3.0 video model in Model Studio: text, image, video and audio in; 480P to 1080P, up to 30 seconds. For film: Text-to-video, first-last frame and reference video in one model, generated faster. Source: https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime https://ai-fieldnotes.com/model-drops/#2026-10-07-anthropic-claude-haiku-5-5 https://ai-fieldnotes.com/model-drops/#2026-10-07-anthropic-claude-haiku-5-5 Wed, 07 Oct 2026 12:00:00 GMT Credit: Anthropic. Anthropic's fastest small model yet, around 75% cheaper to run than Haiku 4.5 on average. Source: https://www.anthropic.com/news/claude-haiku-5-5 https://ai-fieldnotes.com/model-drops/#2026-10-07-shengshu-vidu-q4-preview https://ai-fieldnotes.com/model-drops/#2026-10-07-shengshu-vidu-q4-preview Wed, 07 Oct 2026 12:00:00 GMT Credit: Shengshu. Preview of the next Vidu model: image and reference-to-video with native audio, 3 to 16 second clips, 2K/4K out. For film: Up to 15 image and 3 voice references, with multi-shot camera moves in one take. Source: https://www.vidu.com/vidu-q4