May 19, 2025

Kling AI: Artificial Analysis: Kling 2.0 leads AI video generation, outperforming Veo 2 and Runway Gen-4 in image-to-video tasks. It also ranks second in text-to-video, just behind Sora. https://x.com/ArtificialAnlys/status/1922299716051796148

May 17, 2025

Wan by Alibaba: Five days left to take advantage of Wan's online platform membership sake (till May 23). Get 50% off plus 1 month free if you sign up for yearly plan, which starts as low as $60.

May 16, 2025

Higgsfield AI: Higgsfield drops Short Ads video templates which turn a product photo into a cinematic ad with pro camera moves. Only available to Pro subscribers starting at 29 USD per month.

May 16, 2025

Hunyuan Video: Tencent has launched Hunyuan Image 2.0, an AI image generation model featuring real-time text-to-image capabilities. It claims to respond in milliseconds, significantly faster than current industry standards. The model aims to produce more realistic textures by using a structured rewriting model and specialized reward functions. A new Dual-Canvas Studio feature allows synchronized editing with AI-managed lighting and perspective adjustments.

May 15, 2025

VACE: Wan2.1-VACE is here, a new video creation and editing model available in 1.3B and 14B sizes under the Apache-2.0 license. The model supports reference-to-video generation, video-to-video editing, and masked video editing. It uses multimodal inputs to improve control and allows combining features for more complex video tasks.

May 15, 2025

LTX-Video by Lightricks: LTXV-13b-0.9.7-distilled GGUFs are here. Run the latest LTX Video on limited consumer GPU power in ComfyUI.

May 14, 2025

Speech by Minimax: MiniMax's Speech-02-HD tops the TTS leaderboard https://artificialanalysis.ai/text-to-speech outperforming OpenAI & ElevenLabs in zero-shot voice cloning.