falNew model· 10 days agofal Research released H3 Max, a post-trained version of MiniMax H3 optimized for speed. According to their evaluations, H3 Max ranks first in quality and speed compared to leading video models.
falOpen-weight release· 13 Jul fal released the open-source 3DREAL Strong v2 adapter, a LoRA for LTX 2.3 that turns grey 3D blockouts into photoreal footage with exact composition and camera control.
FASHN, building on fal, provides AI-powered tools for fashion brands to generate on-model imagery at catalog scale and for consumers to perform virtual try-on.
falCapability change· 9 Jul fal announced a 6x speedup in serving Ideogram V4, reducing 1K resolution generation time from 2.75 s to 0.44 s without visible quality loss.
fal achieved 16 times higher throughput on Qwen3.6 for the Ideogram V4 prompt expander using DSpark on SGLang, reaching 700 tok/s after retraining a DFlash model on 250K prompt expansion samples from…
The marketing and growth lead at fal describes how the company uses AI selectively in marketing workflows for tasks such as production mockups, creative exploration, and quickly visualizing ideas,…
falPartnership· 19 May fal announced a strategic partnership with Amazon Web Services (AWS) to use AWS's global scale and reliability for generative media inference workloads.
falSafety or policy· 15 May fal, an AI infrastructure company, detailed its trust and safety posture, including proactive integration of Thorn for CSAM detection and a partnership with StopNCII.org for non-consensual intimate…
falNew model· 10 Apr fal introduced PATINA, a model that generates high-resolution PBR maps from rendered images, bridging the gap between AI-generated images and traditional CGI workflows.
falNew model· 24 Mar fal announced the addition of Inworld TTS-1.5 Max, a text-to-speech model offering low-latency speech generation (time-to-first-audio under ~250ms), improved expressiveness, and support for 15…
falDeveloper tool· 19 Mar fal launched the fal MCP Server, a hosted endpoint that lets AI assistants search, run, and chain over 1,000 generative AI models directly from a conversation.
falAvailability change· 2 Mar HeyGen's models are now available on the fal platform, providing capabilities such as a video agent API, avatar IV API, video translation, and avatar video generation.
fal.ai published an independent prompting guide for Seedream 5.0 Lite, a model released in February 2026.
falResearch paper· 23 Feb fal presents experiments on overlapping communication and computation in the pre-attention stage of Ulysses context parallelism for video diffusion models.
Triton provides an inline_asm_elementwise function that allows injecting elementwise PTX instructions into Triton kernels.