Capability timeline
Vendor-reported claims · May 18, 2025 to Nov 18, 2026
One changeZoom into nearby datesRelease examples
Select a date or a cluster to zoom.
- Reference consistency
- Partial edits
- Resolution
- Image to video
- SVG output
- Drawing interchange
Changes in view
Compare changes
Capability records
Browse dated announcements, model names, and official sources.
Reference consistency · 24 records
Higgsfield ·
A studio that turns a script into a short series: it splits the text into episodes, builds the cast, locations, and props, and generates the episodes with the same characters throughout.
Higgsfield · Gemini Omni Flash 1.2 ·
It works from text, images, and video; references keep characters and objects consistent, per Google, and a reference video’s audio is ignored.
ChatGPT image · ChatGPT Images 2.6 ·
Our new image generation model creates images faster and is better at preserving details across edits, like a character’s outfit when you change the background.
Official source Open on timeline View archive entry Read the article
Higgsfield · Nano Banana 2.1 ·
References: up to 14 images, with consistency for up to 4 characters and up to 10 objects.
Higgsfield · Nano Banana 2.1 ·
Compared with Nano Banana 2, it improves visual quality, prompt adherence, character consistency across edits, and text rendering, per Google.
Higgsfield · Grok Imagine Video 1.5 ·
References: up to 7 images to keep a character or style consistent across generations.
Higgsfield · Grok Imagine Video 1.5 ·
Video extension: continue a clip from its last frame, keeping the character, lighting, and motion consistent.
Higgsfield · GPT Image 2.5 Flare; GPT Image 2.5 Sunburst ·
Both: sharper detail, better subject preservation from references, targeted edits that hold up across iterations, and stronger style holding.
Higgsfield · MiniMax H3 Max ·
Image-to-video: animates a source image, keeping its composition, identity, and aspect ratio, per MiniMax.
Higgsfield · Wan 3.0; Wan 3.0 Prime ·
Consistency: faces, clothing, and details hold across frames, even with several characters.
Grok · Grok Imagine Image 2.0 ·
One world from a handful of prompts: a character, her locations, and the props she carries — generated separately, holding one style from image to image.
Grok · Grok Imagine Video 1.5 ·
Pass in a character image and a voice reference, and both hold — the same face and the same voice in every scene.
Grok · Grok Imagine Video 1.5 ·
Each reference image locks one thing in place — a face, a product, a location.
Grok · Grok Imagine Video 1.5 ·
Keep a character and swap the scene, keep the scene and swap the character, or hold both and change only the action.
Higgsfield · Gemini Omni Flash ·
Consistent characters: face, outfit, and voice hold across edits, with no recasting.
Higgsfield ·
Fights, chases, and explosions are generated with real weight and inertia; face, body, and clothing stay consistent across the video; sound effects, speech, and background music are generated with the video.
Higgsfield ·
A 15-image set of the same character in different poses, outfits, and locations, generated in one run.
Higgsfield · Seedream 5.0 Lite ·
Consistency: a character’s face, clothing, and details hold better across images.
Higgsfield · Omni 3.0 ·
Kling Omni: text, images, video, and audio in one model; generates dialogue, sound effects, and lip-synced speech with the video, keeps characters consistent from references, and handles multi-character scenes.
Runway · Gen-4 References ·
An updated version of Gen-4 References that significantly improves object consistency and prompt adherence. Available for all users.
Official source Open on timeline View archive entry Read the article
Midjourney · Midjourney V7 ·
Omni-reference (--oref) lets you put consistent characters and objects into scenes
Official source Open on timeline View archive entry Read the article
Higgsfield · Veo 3.1 · Date unconfirmed
Upload reference images or videos to lock in a specific style, character, or aesthetic for unlimited generations.
Higgsfield · Date unconfirmed
The AI Video Generator lets you replace faces inside cinematic scenes, edit every image with surgical precision, and maintain perfect character and lighting consistency from the first shot to the last.
Higgsfield · SoulID · Date unconfirmed
It connects directly with other Higgsfield features like SoulID, which ensures consistent identity across projects, and Sora 2, which adds cinematic realism and motion control.
Partial image and video edits · 10 records
Higgsfield · Seedream 5.5 ·
Editing: edits stack one after another, and the parts you didn’t touch stay as they were.
Higgsfield · Ideogram 4.5 Precise Edit ·
Two modes: Whole image edits the entire picture and scales large files down to about 2K; Select area edits only the framed part and returns the result at the size of the upload.
Higgsfield · Nano Banana 2.1 ·
Text edits: describe what to change, such as a shirt color, and the model edits that part of the image.
Higgsfield · Ideogram 4.5 ·
Text edits: replace or translate text in a design with a prompt, keeping the layout.
Canva ·
Coming soon, motion designers will be able to choose which elements of a Cavalry animation (such as text or color) can be edited directly inside Canva, while the core scene stays locked and on-brand.
Higgsfield ·
Object Swap: changes what you describe; the rest of the frame is designed to stay untouched.
Midjourney · Midjourney V8.2 ·
Changing specific areas of your images (inpainting) or expand your canvas (outpainting)
Grok · Grok Imagine Image 2.0 ·
The magic wand edits the region you point at and leaves the rest untouched.
Canva ·
Swap an image, adjust a headline, or refine a font without affecting anything else, with every element remaining fully layered and editable throughout.
Higgsfield · Omni 3.0 Edit ·
Kling Omni Edit: changes to a specific part of an existing clip without regenerating the whole video.
Output resolution · 61 records
Higgsfield ·
Episodes: each one is planned into scenes and clips, then generated at 480p draft, 720p, or 1080p.
Higgsfield · Seedance 2.5 Flash; Seedance 2.5 ·
Clips come out at 480p or 720p with synchronized audio, per ByteDance, and the same prompt and references can be reused in Seedance 2.5 for the final version at 1080p or 4K.
Higgsfield · Seedance 2.5 ·
The Quality setting now goes up to 4K, alongside 480p, 720p, and 1080p.
Higgsfield · Seedream 5.5 ·
Settings: 1K, 1.5K, or 2K output; nine aspect ratios from 1:1 to 21:9.
Higgsfield · GPT Image 2.6 ·
Settings: quality from Low to Max, 1K, 2K, or 4K, opaque or transparent background, and PNG, GIF, or SVG output.
Higgsfield · Gemini Omni Flash 1.2 ·
Output: 3 to 15 seconds per generation, at 360p, 720p, 1080p, or 4K.
Higgsfield · Kling 4.0 Flash ·
Length and resolution: 3 to 20 seconds at 720p.
Higgsfield ·
Settings: 720p or 1080p, five aspect ratios, and an optional prompt for movement and camera.
Canva · Craft ·
Available now in Canva and to developers through our public API, Craft generates stunning, high-quality images at 2K resolution in any aspect ratio.
Higgsfield · Kling 4.0 ·
Output: 3 to 30 seconds, 720p or 1080p, aspect ratios from 21:9 to 9:16, stereo sound, and voiceover in 9 languages.
Higgsfield ·
Quality: 720p or 1080p.
Higgsfield · Wan 3.0 ·
Limits: clips up to 30 seconds at up to 1080p, in a shared queue, so speed depends on load.
Runway · Seedream 5.0 Flash ·
Seedream 5.0 Flash is now live in Runway MCP. Generate 1K or 2K images from text, or from up to 10 reference images.
Higgsfield ·
Quality: 480p, 720p, or 1080p.
Higgsfield · Nano Banana 2.1 ·
Resolution: 1K by default, 2K, or 4K.
Runway · Seedance 2.5 Draft Mode ·
Agent can now generate with Seedance 2.5 Draft mode, creating fast 480p drafts with post-generation enhancement. Iterate and correct generations faster and cheaper, with Draft mode automatically suggested and easy to toggle on or off.
Higgsfield · Grok Imagine Video 1.5 ·
Output: 480p, 720p, or 1080p; 1 to 15 seconds; 24 fps.
Higgsfield · FLUX 3 Image ·
Resolution: 768p, 1K, 1.5K, 2K, or 4K, with native rendering at 2K and 4K.
Higgsfield · Ideogram 4.5 ·
Resolution: 1K or 2K.
Higgsfield ·
Resolution: 480p, 720p, or 1080p.
Higgsfield · Seedream 5.0 Flash ·
Resolution: 1K, 1.5K, or 2K.
Higgsfield · Seedance 2.5 Draft Mode ·
A two-step mode on Higgsfield: a 480p draft first, then a 1080p render of the one you choose.
Higgsfield ·
Settings: resolution from 1080p to 8K and duration, set in the prompt.
Higgsfield ·
Output: up to 1080p.
Higgsfield · MiniMax H3 Max ·
It caps at 768p, where the base H3 reaches 2K.
Higgsfield · Gemini Omni 1.1 Flash ·
Output: up to 10 seconds per generation, at 360p, 720p, 1080p, or 4K.
Higgsfield · FLUX 3 Video Upscaler ·
It takes any input video and outputs 1080p, 2K, or 4K, with motion and audio sync preserved, per Black Forest Labs.
Higgsfield · Wan 3.0; Wan 3.0 Prime ·
Output: up to 30 seconds per generation, at 480p, 720p, or 1080p.
Runway · Wan 3.0 ·
Wan 3.0 is now available in Runway in tool mode and workflows. Generate near state-of-the-art video with audio, using multiple image, video, and audio reference inputs, at 480p, 720p, or 1080p.
Runway · Seedance 2.5 ·
Seedance 2.5 now generates in 1080p across all surfaces. Get sharper, higher-resolution results wherever you create.
Runway · Grok Imagine Video 1.5 ·
xAI's Grok Imagine 1.5 is now available in Runway MCP as grok-imagine-1.5, supporting text-to-video and image-to-video from any MCP client. Generate 1-15 second clips with native audio, up to 1080p resolution.
Higgsfield · Seedance 2.5 ·
Resolution: 480p and 720p, with upscaling up to 4K.
Grok · Grok Imagine Video 1.5 ·
Text-to-video and native 1080p are generally available on grok.com/imagine, iOS, and Android.
Runway · Seedance 2.0 ·
Runway MCP now supports Seedance 2.0 video generation in 4K resolution. Just explicitly request 4K to generate at the higher resolution.
Runway · Seedance 2.0 Fast ·
Two new lightweight Seedance 2.0 tiers are now available through Runway MCP. Seedance 2.0 Fast delivers quick 480p/720p turnaround with full text-to-video, image-to-video, audio, and keyframe support, while Seedance 2.0 Mini offers the cheapest and fastest option for rapid iteration, free in explore mode.
Runway · Nano Banana 2 ·
Nano Banana 2 is now available in Runway MCP. Generate images at 1K, 2K or 4K resolution for 7 credits per image, a more affordable option for experimentation.
Runway · Seedream 5.0 ·
Seedream 5.0 is now available as an image model in tool mode. Use up to 14 reference images and generate at 2K or 3K resolution across eight aspect ratios.
Higgsfield · Nano Banana 2 Lite ·
Google's fast, low-cost image model at 1K is now on Higgsfield, for rapid iterations, bulk content, and social previews before a hi-res final.
Higgsfield · Gemini Omni Flash ·
Google DeepMind's video model is now on Higgsfield in preview (beta): 720p, clips of 4, 6, 8, or 10 seconds, 16:9 or 9:16, with native audio.
Higgsfield · Seedance 2.0 Mini ·
Resolution: 480p and 720p.
Higgsfield · Seedance 2.0 ·
A 4K resolution option is now in Seedance 2.0, which removes the separate upscale step for large-screen output.
Grok · Grok Imagine Video 1.5 Fast ·
Grok Imagine Video 1.5 Fast almost doubles generation speed: it produces 6-second, 720p videos in about 25 seconds, down from 40+ seconds in our previous model.
Official source Open on timeline View archive entry Read the article
Higgsfield ·
Resolution: 2K or 4K, with no per-model tuning.
Grok · grok-imagine-video-1.5-preview ·
You can generate clips at up to 720p.
Higgsfield · Recraft v4.1 ·
Brand controls: a palette of up to 10 colors, a background color, and 1K or 2K output.
Midjourney · Midjourney V8.1 ·
A new Rerun as HD button makes it easy to rerun any V8.1 image generated in Standard Definition (SD) as High Definition (HD).
Higgsfield ·
Upscale: up to 4K or 8K with detail restoration.
Higgsfield ·
Models: 16+ for images, up to 4K in any aspect ratio, and 17+ for video, up to 15 seconds with duration, genre, and start and end frame control.
Higgsfield · Kling 3.0; Kling Omni ·
Kling 3.0 and Kling Omni now support 4K
Higgsfield · GPT Image 2.0 ·
Output goes up to 4K, with marketing visuals, mockups, and packaging as the main use cases.
Higgsfield · Seedance 2.0 ·
Seedance 2.0 now supports 1080p
Midjourney · Midjourney V8.1 ·
We’ve also added a button called “Run as HD” which will rerun any SD job as HD.
Higgsfield · Veo 3.1 Lite ·
Veo 3.1 Lite (Google): fast video at 720p or 1080p, up to 8 seconds, text-to-video and image-to-video with native audio.
Higgsfield · Wan 2.7 ·
Wan 2.7 (Alibaba): 1080p video up to 15 seconds, first and last frame control, 9-grid input, native audio, instruction-based editing, multi-reference support.
Midjourney · Midjourney V8 ·
V8 brings a new --hd mode which natively renders images at 2K resolution and a --q 4 mode if you need a little bit of extra coherence.
Official source Open on timeline View archive entry Read the article
Higgsfield · Nano Banana 2 ·
Formats: 1K, 2K, and 4K output, plus new 1:4, 4:1, 1:8, and 8:1 aspect ratios.
Higgsfield · Kling 3.0 ·
Kling 3.0: video from a prompt or an image, clips from 3 to 15 seconds at 720p or 1080p.
Higgsfield · Veo 3.1 ·
Veo 3.1 now supports 4K
Grok · Grok Imagine Video 1.5 · Date unconfirmed
`grok-imagine-video-1.5` now supports text-to-video, image-to-video, and reference-to-video (including optional preset voices), with native 1080p for T2V and I2V.
Higgsfield · Kling 2.5 Turbo · Date unconfirmed
Kling 2.5 Turbo generates 1080p videos - which means high-quality final results without downscaling issues.
Higgsfield · Veo 3.1 · Date unconfirmed
Veo 3.1 videos have 1080p native quality, longer duration, and broader creative control - bringing a new level of cinematic storytelling to creators.
Image-to-video generation · 27 records
Higgsfield · Gemini Omni Flash 1.2 ·
It works from text, images, and video; references keep characters and objects consistent, per Google, and a reference video’s audio is ignored.
Higgsfield · Kling 4.0 ·
It generates from text, an image, or a set of references and can edit finished clips.
Higgsfield · Grok Imagine Video 1.5 ·
Modes: image-to-video, text-to-video, reference-to-video, and video extension.
Higgsfield ·
Ads and UGC: product ads, video ads, UGC videos, and Ad Multiplier variations from one photo or video.
Higgsfield · Seedance 2.5 Draft Mode ·
First and last frame: upload a start image and an end image, and the model fills in the motion between them.
Higgsfield · MiniMax H3 Max ·
Image-to-video: animates a source image, keeping its composition, identity, and aspect ratio, per MiniMax.
Higgsfield · Gemini Omni 1.1 Flash ·
First and last frame: set both and the model generates everything in between.
Runway · Grok Imagine Video 1.5 ·
xAI's Grok Imagine 1.5 is now available in Runway MCP as grok-imagine-1.5, supporting text-to-video and image-to-video from any MCP client. Generate 1-15 second clips with native audio, up to 1080p resolution.
Runway · Seedance 2.5 ·
Seedance 2.5 is now available in Runway MCP. Generate up to 30 seconds of video with native audio, using text-to-video, image-to-video, or video-to-video, with first frame, last frame, and reference image controls, all directly from your AI agent.
Runway · MiniMax Hailuo 3.0 ·
MiniMax Hailuo 3.0 is now live on Runway Dev. Generate video from text, image, or video, with support for keyframes plus reference images, videos, and audio.
Runway · Seedance 2.0 Fast ·
Two new lightweight Seedance 2.0 tiers are now available through Runway MCP. Seedance 2.0 Fast delivers quick 480p/720p turnaround with full text-to-video, image-to-video, audio, and keyframe support, while Seedance 2.0 Mini offers the cheapest and fastest option for rapid iteration, free in explore mode.
Higgsfield · Kling 3.0 Turbo ·
It supports text-to-video and image-to-video.
Grok · Grok Imagine Video 1.5 ·
These are our best image-to-video models yet: better motion, better physics, better audio, at the fastest speeds.
Official source Open on timeline View archive entry Read the article
Grok · grok-imagine-video-1.5-preview ·
grok-imagine-video-1.5-preview turns a single still image into fluid, cinematic video.
Higgsfield · Grok Imagine 1.5 ·
It animates a still image, using it as the first frame, and is designed to keep its composition and style.
Higgsfield ·
A tool that makes ad videos from a product photo or link, with an avatar and a format of your choice.
Runway · Seedance 2.0 ·
Use anything—text, image, video or audio—to generate or edit videos with Seedance 2.0. Now available on Unlimited and Enterprise plans outside the US.
Higgsfield · Veo 3.1 Lite ·
Veo 3.1 Lite (Google): fast video at 720p or 1080p, up to 8 seconds, text-to-video and image-to-video with native audio.
Higgsfield · Kling 3.0 ·
Kling 3.0: video from a prompt or an image, clips from 3 to 15 seconds at 720p or 1080p.
Grok ·
Transform your photos into cinematic videos with realistic motion, object interactions, and visual continuity.
Runway · Gen-4.5 ·
You can now supply a first frame image alongside your text prompt with Gen-4.5.
Official source Open on timeline View archive entry Read the article
Midjourney ·
2) You can now make videos with a specific start and end images
Official source Open on timeline View archive entry Read the article
Midjourney · Midjourney Video Model V1 ·
Today’s Video workflow will be called “Image-to-Video”.
Grok · Grok Imagine Video 1.5 · Date unconfirmed
`grok-imagine-video-1.5` now supports text-to-video, image-to-video, and reference-to-video (including optional preset voices), with native 1080p for T2V and I2V.
Higgsfield · Kling O1 · Date unconfirmed
Upload a single image → get a 5, 10 second cinematic clip.
Higgsfield · Date unconfirmed
Now, meet Urban Cuts - the new Higgsfield feature designed to turn your static look into a full beat-synced outfit video generated from just a single photo.
Higgsfield · Kling 2.5 Turbo · Date unconfirmed
Kling 2.5 Turbo stands out because it introduces structured video generation built around clear anchor points: a Start Frame and an End Frame.
SVG generation · 5 records
Higgsfield · GPT Image 2.6 ·
Besides standard images, it makes animated GIFs, vector SVGs, and generates on a transparent background.
Higgsfield · Ideogram Vector 1.0 ·
Ideogram’s model for vector graphics is now on Higgsfield: SVG logos, icons, and illustrations from a prompt or an existing image.
Higgsfield · Ideogram Vector 1.0 ·
Image to SVG: one image converted into editable vector shapes; no prompt needed.
Higgsfield ·
In Figma: image generation across models, Vector Generation (SVG), Mockup Studio, Remove Background, Color Grading, Expand, Relight, Angles, and Face Swap.
Higgsfield · Recraft v4.1 ·
Recraft's model for design work is now on Higgsfield: typography, clean lines, brand visuals, and editable SVG vectors straight from a prompt.
Drawing interchange · 6 records
Autodesk Forma ·
Import a DXF into the floor plan and trace over it to build your plan.
Autodesk Forma ·
We know some of our customers still prefer the reliable workflows that AutoCAD offer, so now you can take a floor plan design from Forma Building Design into AutoCAD as a DWG file, so you can continue working on your model instead of redrawing it from scratch.
Autodesk Forma ·
You control which buildings, components, labels, and units go into each export, so you can tailor the file to the job: a fuller export to continue technical design, or a lighter one for polished floor plan drawings.
Autodesk Forma ·
Totals by type feed into the area metrics panel, and the DXF export carries parking on its own layer.
Autodesk Forma ·
Furniture is also included in the Revit export as families or as blocks in DWGs of course.
Autodesk Forma ·
Design them in floorplan view, and they appear in the 3D scene, in sections and, of course, in the Revit export.
Release examples · 1 records
Midjourney · Midjourney V8.2 ·
Midjourney opened testing of its V8.2 edit model with instruction-based edits, up to four image references, inpainting, and canvas expansion.
