TITAA #93: Hands-On Tests of Mischief-1 and Kling v4 Video Models, From $0.01/sec
arnicas · x · 2026-11-02
Lynn Cherny's resource-rich newsletter TITAA #93 leads with hands-on tests of new AI video tools:
- Mischief-1: a new fast video model on fal. Animating public-domain book illustrations (a hard case for non-photoreal styles) showed little style drift; costs only $0.01/sec.
- Kling v4: now out with image, reference, and video editing modes; cheaper than Seedance with strong consistency — a longer prompt on the same start image yielded an even more faithful result at $0.0157/sec.
- FLUX 3 Max Keyframes to Video: fal's keyframe-to-video lets you generate multi-scene, reference-consistent clips from multiple images in one pass, avoiding stitching.
- The issue also rounds up character AI, 3D/world models, games, and OCR resources, including Claudia, an "open source" AI singer with full production docs for her eight music videos at claudia.gallery.
Related event: TITAA #93 Tests Mischief-1 and Kling v4 Video Models(2 posts)→
More from Multimodal
- PRISM-DMAD-PDMD merge nails realistic skin in 8 steps, no Turbo LoRA — theOliviaRossi · 2026-11-02
- REC Frame Overlay: ComfyUI Node Adds Viewfinder and Y2K Digicam HUDs to Image/Video Batches — Hour-Shower-4028 · 2026-11-02
- Pika speeds up video generation 60% with pure inference engineering in H3 Flex — ghumare64 · 2026-11-02
- AI Prompt Turns Ordinary Product Shots into Premium Commercial Ads — anthara_ai · 2026-11-02
- Photo Restoration Prompt: Deblur Old Photos Without Inventing Details — anthara_ai · 2026-11-02
- Prompt to Turn Casual Photos into Professional LinkedIn Headshots — anthara_ai · 2026-11-02