- fal.ai
minimax/h3-max-turbo/reference-to-video
Fal.ai introduced a new video generation model, minimax/h3-max-turbo/reference-to-video, enabling users to create up to 15-second videos from text prompts and image, video, or audio references at 480p…
- fal.ai
mureka/v9.5/generate/song
Fal introduced mureka/v9.5/generate/song, a text-to-audio API that generates original songs from prompts or lyrics with controls for style, vocals, and melody. The model supports commercial use, strea…
- Featurefal.ai
mureka/v9.5/generate/soundtrack
Fal introduced a new soundtrack generation feature in mureka v9.5, enabling users to create audio tracks from uploaded images or videos with optional style and mood controls. The feature costs $0.10 p…
- fal.ai
mureka/v9.5/generate/instrumental
Fal introduced mureka/v9.5, a new version of its text-to-audio model optimized for instrumental music generation. The API generates instrumental tracks from text prompts or uploaded references, suppor…
- fal.ai
mureka/v9/generate/soundtrack
Fal introduced mureka/v9/generate/soundtrack, a new model that generates soundtracks from images or videos with optional style and mood guidance. Each soundtrack costs $0.10, with bulk pricing at $1 f…
- Launchfal.ai
mureka/v9/generate/instrumental
Fal introduced mureka/v9/generate/instrumental, a new AI model that generates instrumental music from text descriptions or uploaded references. The model supports commercial use, streaming, and costs …
- Launchfal.ai
mureka/v9/generate/song
fal.ai introduced mureka/v9/generate/song, a new API endpoint that generates full songs from text prompts or lyrics with fine-grained controls for style, vocals, melody, and reference audio. The model…
- fal.ai
speridlabs/idol
Fal introduced speridlabs/idol, a model that converts a single image into a 3D Gaussian splat with GLB point-cloud previews. The API costs $0.1 per generation and provides downloadable outputs includi…
- Launchfal.ai
bytedance/seedance-2.5/us/draft/complete
Fal introduced the Seedance 2.5 US Draft Complete API, enabling users to regenerate video tasks at 1080p resolution using a draft ID. The endpoint supports commercial use and charges $1.164 per second…
- fal.ai
tbc/mischief-1/image-to-video
Fal introduced tbc/mischief-1/image-to-video, a neuron-derived video model that generates videos 5x faster and at lower cost than alternatives. The model supports 480p and 720p resolutions, with prici…
- Featurefal.ai
fal-ai/motion-to-code/glsl
Fal added a GLSL shader generation capability to its motion-to-code toolkit, enabling users to convert text prompts, images, or videos into looping GLSL shaders playable in a live preview. The feature…
- Launchfal.ai
fal-ai/motion-to-code/gsap
Fal.ai released a new model, motion-to-code/gsap, that transforms text prompts, images, or videos into self-contained GSAP animations delivered as editable HTML pages. The output is a single HTML file…
- Launchfal.ai
veed/dubbing
Fal introduced veed/dubbing, a new model that dubs videos up to 10 minutes long into 86 languages using cloned voices and lip-sync while preserving tone and emotion. Pricing is $0.11 per second of inp…
- fal.ai
kling/v4/image-to-video
Fal introduced kling/v4/image-to-video, a new API that converts static images into 3–30 second videos at 720p or 1080p resolution. The model supports optional start/end frames, per-shot prompts, and m…
- Launchfal.ai
veed/dubbing/pro
Fal.ai introduced veed/dubbing/pro, a new AI model that dubs videos up to 10 minutes into 94 languages and 14 regional accents with cloned voices and lip-sync. The model supports accent control, multi…
- Sunsetfal.ai
fal-ai/kling-video/v2.1/master/image-to-video
Fal’s Kling 2.1 Master image-to-video API endpoint has been officially deprecated and is no longer supported, with pricing details still listed but usage discouraged. Users are directed to try similar…
- fal.ai
blackforestlabs/flux-3/klein/base/trainer/edit
Fal introduced a trainer/edit feature allowing users to fine-tune the FLUX 3 Image Klein model using before/after image pairs, enabling custom edit capabilities. Training costs $0.002 per step, scalin…
- Featurefal.ai
blackforestlabs/flux-3/klein/base/trainer
Fal introduced a LoRA-based trainer for blackforestlabs' FLUX 3 Image Klein model, enabling users to fine-tune the model with custom images for subject, product, or style training. The tool costs $0.0…
- fal.ai
blackforestlabs/flux-3/klein/edit-image/lora
Fal introduced a new model endpoint, blackforestlabs/flux-3/klein/edit-image/lora, enabling fast image editing with distilled FLUX 3 Image Klein and support for up to three custom LoRAs. The model all…
- fal.ai
vast/eden-live-5b-game
Fal introduced vast/eden-live-5b-game, a 5B-parameter model for real-time game rendering using VAST's Eden Live technology. The model supports commercial use, async API, and LLM integration, with 13 p…
- fal.ai
vast/eden-live-14b-video
Fal introduced vast/eden-live-14b-video, a 14B-parameter video-to-video generative model enabling real-time restyling of videos from any reference input. The model supports commercial use, async API, …
- fal.ai
vast/eden-live-14b-game
Fal introduced vast/eden-live-14b-game, a 14B-parameter model enabling real-time game rendering and interactive gameplay via VAST's Eden Live technology. Users can select from 13 playable games, custo…
- Launchfal.ai
vast/eden-live-5b-video
Fal introduced vast/eden-live-5b-video, a 5B-parameter video-to-video generative model enabling real-time restyling of videos using scene descriptions and reference frames. Sessions cost $0.0035 per s…
- fal.ai
ideogram/vector/text-to-vector
Fal introduced ideogram/vector/text-to-vector, a model that generates editable SVG vector graphics from text prompts with optional reference images, three quality tiers, and aspect ratio controls. Pri…
- Launchfal.ai
ideogram/vector/image-to-vector
Fal introduced a new model, ideogram/vector/image-to-vector, which converts raster images into editable SVG vector graphics. The service offers two modes (default for detail, simple for fewer shapes) …
- fal.ai
heygen/heygen-video/image-to-video
Fal introduced the HeyGen Video Image-to-Video API model, enabling users to animate static images into 5–15 second video clips with generated sound. The model is built on MiniMax H3 and post-trained b…
- Launchfal.ai
heygen/heygen-video/reference-to-video
Fal introduced the heygen/heygen-video/reference-to-video model, enabling users to create 5–15 second video scenes from reference images, videos, or audio while preserving product, people, or place de…
- fal.ai
heygen/heygen-voice
Fal introduced heygen/heygen-voice, a text-to-speech model enabling natural speech synthesis using library voices or instant voice cloning from a reference audio clip. The model costs $0.03 per 1,000 …
- Launchfal.ai
heygen/heygen-voice/turbo
Fal introduced HeyGen Voice Turbo, a faster and lower-cost tier of HeyGen Voice, enabling instant voice cloning from a reference clip with library voices. The model costs $0.004 per 1,000 input charac…
- fal.ai
heygen/heygen-video/text-to-video
Fal introduced heygen/heygen-video/text-to-video, a new AI model that generates 5–15 second video clips from text prompts, post-trained by HeyGen on MiniMax H3. The model is available via Fal’s platfo…
- fal.ai
kling/v4/text-to-video
Fal introduced kling/v4, a text-to-video model generating 3–30 second videos at 720p or 1080p resolution with per-shot prompt support. Pricing is $0.157/second at 720p and $0.235/second at 1080p, with…
- Launchfal.ai
Fal introduced kling/v4/image-to-video, a new API that converts static images into 3–30-second videos at 720p or 1080p resolution. The model supports optional ending frames, per-shot prompts, and comm
- Featurefal.ai
kling/v4/reference-to-video
Fal.ai introduced kling/v4/reference-to-video, enabling video creation from text prompts combined with image or video references at 720p or 1080p resolutions and 3–30 second durations. The model suppo…
- fal.ai
kling/v4/video-to-video/edit
Fal introduced kling/v4/video-to-video/edit, enabling AI-driven video edits using text prompts and optional image references. The model outputs 3–30-second videos at 720p ($0.094/sec) or 1080p ($0.141…
- Launchfal.ai
bytedance/seedance-2.5/us/image-to-video
Fal.ai introduced a new API endpoint for ByteDance’s Seedance 2.5 model, enabling US-hosted image-to-video generation with synchronized audio and optional end-frame control. Videos can be produced up …
- fal.ai
blackforestlabs/flux-3-max/image-to-video
Fal introduced FLUX 3 Max, a post-trained variant of FLUX 3 Video optimized for stronger prompt adherence, visual quality, and lower latency. The new model supports image-to-video generation with conf…
- fal.ai
krea/v3/text-to-image
Fal introduced krea/v3, a new text-to-image API powered by FLUX 3 Max, offering prompt expansion, configurable output dimensions, and seed control. The API supports commercial use, provides JavaScript…
- fal.ai
minimax/h3-max/reframe-video
Fal introduced minimax/h3-max/reframe-video, a generative AI model that expands existing videos to selected aspect ratios while preserving source audio and timing. The model supports 480p or 768p outp…
- Launchfal.ai
bria/fibo-2/edit
Fal introduced Fibo 2.0 Edit, an instruction-based image editing model enabling targeted edits like background swaps and product restaging while preserving commercial rights. Trained on licensed data,…
- fal.ai
bria/fibo-2/generate
Fal introduced bria/fibo-2/generate, a new text-to-image model trained exclusively on licensed data with clear commercial rights, optimized for reasoning and knowledge-heavy prompts. The endpoint supp…
- Featureblog.fal.ai
EAGLE-4 Technical Deepdive
Fal.ai, in collaboration with Fireworks, launched EAGLE-4, a next-generation speculative decoding system for AI models. EAGLE-4 introduces branching verification trees and a hardware-aware harness tha…
- Launchfal.ai
blackforestlabs/flux-3-max/text-to-video
fal.ai introduced FLUX 3 Max, a post-trained variant of FLUX 3 Video optimized for lower latency and higher prompt adherence, now available via their platform. The model generates 5–20 second videos f…
- fal.ai
blackforestlabs/flux-3-max/keyframes-to-video
Fal introduced FLUX 3 Max Keyframes-to-Video, a post-trained variant of Black Forest Labs’ FLUX 3 Video optimized for lower latency and stronger prompt adherence. The model supports up to ten keyframe…
- fal.ai
fal.ai introduced FLUX 3 Max, a post-trained variant of FLUX 3 Video optimized for image-to-video generation with stronger prompt adherence and lower latency. The model ranks joint #1 in preliminary i
- fal.ai
Z-Image TurboGenerate Images at the Speed of Thought
Fal introduced Z-Image Turbo, a 6-billion-parameter text-to-image model delivering images in under a second via a serverless API. It supports LoRA, ControlNet, inpainting, and image-to-image transform…
- Integrationfal.ai
Grok ImagineImage and Video Generation by xAI
Fal now offers xAI’s Grok Imagine family—text-to-image, image editing, and video generation up to 1080p with native audio—via a single serverless API. Developers can access all models (including Grok …
- Integrationfal.ai
ElevenLabsThe Voice of AI
Fal.ai now offers ElevenLabs' entire audio AI suite—including Eleven V3, Turbo v2.5, Multilingual v2, Scribe v2, Music, voice changer, and dubbing—through its serverless API. The integration provides …
- Launchfal.ai
robbyant/lingbot-world-2
Fal introduced robbyant/lingbot-world-2, a new AI model enabling real-time interactive 3D world exploration with movement and camera controls. The model generates photorealistic environments with natu…
- Launchfal.ai
bytedance/omnihuman/v2
Fal introduced bytedance/omnihuman/v2, a model that generates high-quality videos from a human image and audio input, with emotions and movements synchronized to the audio. The model costs $0.105 per …
- fal.ai
Fal introduced Krea 3, a new text-to-image model API that generates images from text prompts with optional prompt expansion, configurable output dimensions, and seed control. The model is billed at $0
- fal.ai
blackforestlabs/flux-3/klein/base/edit-image
Fal.ai introduced flux-3/klein/base/edit-image, enabling edits and compositions from text instructions with up to ten reference images. The model supports configurable guidance, negative prompts, and …
- fal.ai
blackforestlabs/flux-3/klein/base/text-to-image
Fal.ai introduced a new text-to-image model, blackforestlabs/flux-3/klein/base/text-to-image, powered by FLUX.3 Klein Base, with configurable settings like guidance, negative prompts, and layout contr…
- Launchfal.ai
blackforestlabs/flux-3/klein/edit-image
Fal introduced flux-3/klein/edit-image, enabling edits and compositing of images from text instructions with up to ten reference images and optional bounding-box controls. The model supports commercia…
- fal.ai
blackforestlabs/flux-3/klein/text-to-image
Fal.ai introduced the blackforestlabs/flux-3/klein/text-to-image model, enabling commercial text-to-image generation with configurable sizes (768p to 4K) and optional layout control. Pricing ranges fr…
- Launchfal.ai
nvidia/nemotron-3-5-super/video
Fal.ai now hosts NVIDIA’s Nemotron 3.5 Super video model, allowing users to analyze video clips by summarizing actions, identifying moments, and reasoning across frames. The model supports commercial …
- Launchfal.ai
kotoba-technologies/kotoba-tts/v2/tts/ws
Fal.ai introduced kotoba-technologies/kotoba-tts/v2/tts/ws, a WebSocket-based text-to-speech model for Japanese that streams speech in real time. The endpoint costs $0.015 per 1,000 UTF-8 bytes of inp…
- fal.ai
kotoba-technologies/kotoba-sts/v1/realtime_voice
Fal.ai introduced kotoba-sts/v1/realtime_voice, a real-time speech-to-speech translation model enabling users to speak in one language and hear the translation in another. The model streams audio and …
- Launchfal.ai
kotoba-technologies/kotoba-streaming-stt/v1/realtime
Fal introduced a new real-time streaming speech-to-text model, kotoba-streaming-stt/v1/realtime, enabling live transcription over WebSocket with partial results. The model is priced at $0.39 per hour …
- Featurefal.ai
bria/fibo-edit-1.5/expand
Fal introduced Bria Expand, an AI model that extends images to any of 9 aspect ratios or custom canvases up to 25 megapixels while preserving original content. Built on FIBO-Edit-1.5, it costs $0.04 p…
- Pricingfal.ai
mirelo-ai/sfx2.0/text-to-audio
Fal.ai’s Mirelo SFX2.0 text-to-audio API now offers a 33% discount on its standard $0.015/second rate, reducing it to $0.010/second from October 14 to December 13, 2026. Billing is based on total outp…
- Launchfal.ai
mirelo-ai/sfx2.0/video-to-video
Fal.ai introduced the mirelo-ai/sfx2.0 video-to-video model, which generates synchronized sound effects for input videos and returns the modified video with a new soundtrack. The model supports text g…
- fal.ai
mirelo-ai/sfx2.0/video-to-audio
Fal introduced mirelo-ai/sfx2.0, a new video-to-audio model that generates synchronized soundtracks from input videos and returns them as audio files. The model supports text guidance, negative prompt…
- fal.ai
Krea 3Krea's AI image editing model
Fal introduced Krea 3, a new AI image editing model enabling reference-driven edits like combining images, maintaining character consistency, restaging products, and repainting rooms while preserving …
- fal.ai
krea/v2/large/text-to-image
Fal introduced Krea 2 Large, a high-fidelity text-to-image model supporting aspect ratio, creativity, seed controls, and style references. Standard generations cost $0.060 per image, while style refer…
- Featurefal.ai
Fal.ai updates inference methods with five calling patterns and Serverless guidance
Fal.ai expanded its inference documentation to detail five distinct calling patterns—direct (run), queue-backed synchronous (subscribe), asynchronous (submit), streaming (stream), and real-time (realt…
- Featurefal.ai
Fal.ai launches real-time WebSocket inference for ultra-low latency image generation
Fal.ai introduced real-time inference via WebSockets for its hosted model APIs, enabling sub-100ms image generation for interactive applications like real-time creativity tools. Unlike queue-based inf…
- fal.ai
Fal launches environment management for Serverless deployments
Fal introduced environment management for its Serverless product, allowing developers to isolate applications, secrets, and configurations across development, staging, and production stages. Each envi…
- Featurefal.ai
Fal launches Error Analytics dashboard for Serverless deployments
Fal introduced an Error Analytics dashboard to help developers debug request errors across their Serverless applications. The tool provides a centralized view of failures, filtering by endpoint, statu…
- fal.ai
google/nano-banana-2.1
Fal.ai now hosts Google’s Nano Banana 2.1 as a text-to-image API, enabling 4K resolution outputs, adjustable aspect ratios, and web search grounding. The model improves visual quality, text rendering,…
- fal.ai
google/nano-banana-2.1/edit
Fal.ai introduced google/nano-banana-2.1/edit, an API endpoint exposing Google’s Nano Banana 2.1 model for image editing tasks. The model supports high-resolution edits (up to 4K), multi-image fusion,…
- fal.ai
bytedance/seedream/v5/pro/edit
Fal.ai introduced Seedream 5.0 Pro, a grounded image editing model enabling precise edits with layer separation and sketch completion. The model supports up to 10 reference images and charges $0.0675 …
- fal.ai
bytedance/seedream/v5/pro/text-to-image
Fal now hosts ByteDance’s Seedream 5.0 Pro, a flagship text-to-image model with deep prompt understanding, multilingual text support, and precise layout control. Pricing is set at $0.0675 per image fo…
- fal.ai
Fal introduced the bytedance/seedream/v5/pro/edit API, a grounded image editing model enabling precise element replacement while preserving the rest of the frame. The model supports layer separation,
- fal.ai
fal-ai/bytedance/seedream/v5/lite/text-to-image
Fal.ai introduced Seedream 5.0 Lite, a fast text-to-image AI model optimized for high-quality output up to 3072x3072 pixels. The model supports batch generation (1-6 images per call), costs $0.035 per…
- fal.ai
Fal.ai now hosts Google’s Nano Banana 2.1, a text-to-image model generating images up to 4K resolution with adjustable aspect ratios and optional web search grounding. The API supports commercial use,
- Launchfal.ai
fal-ai/bytedance/seedream/v5/lite/edit
Fal introduced a new image editing endpoint for Seedream 5.0 Lite, enabling high-quality, fast intelligent edits with multi-image support. The model processes up to 10 reference images per request, ou…
- fal.ai
openai/gpt-image-2.5/flare/text-to-image
Fal.ai introduced GPT Image 2.5, an OpenAI-backed text-to-image model optimized for speed and quality, supporting complex layouts and transparent backgrounds. The model is now available via a new API …
- Featurefal.ai
Fal adds Prometheus-compatible metrics endpoint for Serverless observability
Fal introduced a Prometheus-compatible metrics endpoint for its Serverless platform, enabling users to export real-time metrics to Grafana, Datadog, or other monitoring tools. The endpoint provides de…
- Launchfal.ai
Fal.ai introduced OpenAI's GPT Image 2.5 Flare text-to-image model, positioning it as the default image model for most applications with fast, high-quality generation. The model supports complex layou
- fal.ai
openai/gpt-image-2.5/flare/edit
Fal.ai introduced GPT Image 2.5/flare/edit, enabling precise image edits that preserve subject, composition, and background while keeping reference subjects recognizable across styles. The model suppo…
- Featurefal.ai
Fal introduces advanced scaling parameters for Serverless GPU deployments
Fal updated its Serverless documentation to introduce granular scaling parameters for GPU-based deployments, including min_concurrency, concurrency_buffer, keep_alive, scaling_delay, max_multiplexing,…
- Launchfal.ai
Nano Banana ProReasoning-Powered Visuals, Unmatched Fidelity
Fal introduced Nano Banana Pro, a new image generation and editing model built on Google's Gemini 3 Pro Image. The model uses reasoning-first generation for coherent compositions, accurate text render…
- Launchfal.ai
FLUX.2Next-Generation Visual Intelligence
Fal.ai introduced FLUX.2, a next-generation visual intelligence model developed by Black Forest Labs, featuring a 32B parameter architecture, multi-reference editing (up to 10 images), 4MP output, and…
- Launchfal.ai
krea/v2/medium/text-to-image
Fal introduced Krea 2 Medium, a new text-to-image model offering high-quality image generation with aspect ratio control, creativity settings, seeds, and style references. The model charges $0.030 per…
- Launchfal.ai
minimax/h3-max/relight
Fal.ai introduced minimax/h3-max/relight, a model enabling AI-driven video relighting using a lighting sphere image while preserving subjects, motion, camera, and audio. Pricing is $0.05–$0.32 per sec…
- fal.ai
fal-ai/vidu/q4/reference-to-video
Fal introduced Vidu Q4, a generative video model that creates up to 16-second videos from up to 12 reference images and 3 voice clips while maintaining character, object, and voice consistency. The mo…
- fal.ai
fal-ai/vidu/q4/image-to-video
Fal introduced Vidu Q4, a model that converts a single image into 3–16 second videos with native audio up to 4K resolution. The tool targets animating stills, product shots, and character scenes with …
- fal.ai
mureka/api/generate/song
Fal introduced the mureka/api/generate/song endpoint, enabling users to generate songs from text prompts or lyrics with controls for style, vocals, and melody. Pricing ranges from $0.045 to $0.75 per …
- fal.ai
mureka/api/generate/instrumental
Fal.ai introduced a new API endpoint, mureka/api/generate/instrumental, enabling users to generate instrumental music from text descriptions or uploaded references. The service supports multiple model…
- fal.ai
mureka/api/generate/lyrics
Fal.ai added a new lyrics-generation API endpoint to its mureka model suite, enabling users to generate original song lyrics and titles from text prompts. The endpoint costs $0.0135 per request and su…
- Launchfal.ai
mureka/api/generate/lyrics-video
Fal.ai introduced a new model endpoint, mureka/api/generate/lyrics-video, enabling users to create lyrics videos from generated or uploaded audio. The feature supports customizable layouts, aspect rat…
- Launchfal.ai
mureka/api/generate/podcast
Fal.ai introduced a new API endpoint, mureka/api/generate/podcast, that converts ordered conversation turns into podcast audio with customizable text and voice selections. The feature costs $0.1725 pe…
- fal.ai
Nano Banana 2.1Google's AI image generation and editing model
Fal now offers Google’s Nano Banana 2.1, an AI image generation and editing model, via its API and platform. The update adds mask-based editing, stronger subject consistency, and improved visual desig…
- Launchfal.ai
Fal introduced google/nano-banana-2.1, a Google-developed text-to-image model on its platform, supporting up to 4K resolution, adjustable aspect ratios, and optional web search grounding. Pricing star
- Launchfal.ai
Fal introduced the Google Nano Banana 2.1 Edit API, enabling precise image-to-image transformations with text instructions while preserving identity, expressions, and scene geometry. Outputs support u
- Launchfal.ai
mirelo-ai/sfx-v1/video-to-audio
Fal introduced mirelo-ai/sfx-v1, a new video-to-audio model enabling users to generate synced sound tracks from videos, similar to MMAudio. The model is available via Fal’s platform with a cost of $0.…
- Launchfal.ai
meshy/v6-lite/retexture
Fal.ai introduced meshy/v6-lite/retexture, a new model enabling users to apply new textures to existing 3D models via text prompts or reference images, with optional PBR maps included. The service cos…
- fal.ai
fal-ai/kandinsky6-vsr
Fal introduced Kandinsky 6.0 VSR, a video super-resolution model that upscales and enhances videos with sharper detail and flicker-free frames. The model is available via Fal's platform with a pricing…
- fal.ai
fal-ai/kandinsky6-pro/text-to-video
Fal.ai introduced Kandinsky 6.0 Pro, a high-resolution text-to-video model generating 5-second 480p clips at 50 inference steps for $1.35 per unit. The model emphasizes cinematic motion and precise pr…
- fal.ai
fal-ai/kandinsky6-pro/image-to-video
Fal introduced an image-to-video feature for its Kandinsky 6.0 Pro model, enabling users to convert a single image into a 5-second 480p video clip with controllable motion. The feature costs $1.40 per…
- fal.ai
fal-ai/kandinsky6-lite/image-to-video
Fal introduced Kandinsky 6.0 Lite, a model that converts static images into short, prompt-guided video clips with lightweight inference. The feature costs $0.17 per 5-second 480p video at 10 inference…
- fal.ai
fal-ai/kandinsky6-lite/text-to-video
Fal.ai introduced Kandinsky 6.0 Lite, a lightweight text-to-video model optimized for speed and prompt adherence. The model generates 5-second 480p videos at 10 inference steps for $0.16 per unit, wit…
- Launchfal.ai
fal-ai/kandinsky6-vsr/lite
Fal introduced Kandinsky 6.0 VSR Lite, a lightweight video super-resolution model optimized for quick, cost-efficient upscaling. The model charges $0.00036 per megapixel-frame at 5 inference steps and…
- Launchfal.ai
fal-ai/marigold-v2
Fal introduced Marigold V2, a diffusion-based depth estimation model built on Qwen-Image-Edit, enabling colorized depth map generation from single images. The model is available via Fal's platform wit…
- Launchfal.ai
minimax/h3-max/recast
Fal introduced H3 Max Recast, a new feature enabling users to recast people in videos using reference photos while preserving motion, camera work, cuts, and audio. The feature is billed at $0.30 per s…
- fal.ai
xai/grok-imagine-video/v1.5/lite/image-to-video
Fal.ai introduced the xAI Grok Imagine Video 1.5 Lite model for image-to-video generation, enabling users to create videos from static images. The model is priced per second of output and per input im…
- Launchfal.ai
xai/grok-imagine-video/v1.5/lite/text-to-video
Fal.ai introduced xAI's Grok Imagine Video 1.5 Lite, enabling text-to-video generation with commercial use rights. The model supports 480p ($0.02/sec), 720p ($0.03/sec), and 1080p ($0.14/sec) resoluti…
- fal.ai
minimax/h3-max-turbo/extend-video
Fal.ai introduced a new feature for its H3 Max Turbo model allowing users to extend existing videos by 1–15 seconds with prompt-guided footage. The feature supports resolutions from 480p to 2K and inc…
- fal.ai
blackforestlabs/flux-3/text-to-image, details and endpoints
Fal introduced Flux 3, Black Forest Labs' newest text-to-image model, enabling detailed 2K and 4K image generation with improved text rendering and layout control. The model is available via Fal's API…
- fal.ai
blackforestlabs/flux-3/edit-image, details and endpoints
Fal introduced Flux 3 Image Edit, a new model enabling precise local image edits or multi-reference composition without altering the rest of the image. The model supports up to 10 reference images, te…
Suivez Fal en pilote automatique
- · Brief IA hebdomadaire : résumé narratif de ce qui a été livré, chaque lundi 9 h
- · Alertes par e-mail ou Slack, ou discutez avec l'archive depuis votre tableau de bord
- · Ajoutez Fal + jusqu'à 2 autres concurrents gratuitement, sans carte bancaire