Higgsfield
Higgsfield is a hosted AI video studio. You can drive it from Claude through its MCP and skills, use Soul characters for consistency, and use Katana for reference-driven edits. It runs on credits. This hub also tracks the open-source rebuilds of Higgsfield-style apps.
Lab posts (20)
- HeyGen Avatar 6 lands at #1 on Avatar Arena and in ComfyUI the same day, plus HyperFrames 0.9.64 and a Miracle update
HeyGen shipped Avatar 6, its new talking-avatar model, on Tuesday morning. Within two hours an independent blind-vote arena had it at #1, and by lunch it was available as a ComfyUI Partner Node. HeyGen's open-source HyperFrames also put out v0.9.64, and Higgsfield posted an update on its Miracle layer editor.
- Weekend release run: HyperFrames 0.9.43 to 0.9.58, Remotion 4.0.544 adds OpenTimeline export, and Seedance 2.5 Flash lands in ComfyUI
HeyGen shipped fifteen HyperFrames releases between Friday afternoon and this morning, mostly about safety and stability. Remotion 4.0.544 can now export a Studio timeline to OpenTimeline and deploy Lambda with Terraform. ComfyUI added Seedance 2.5 Flash as a partner node, and Kling teased Image 4.0.
- LTX pits Alpha Gen against Bria and CorridorKey, Bria RMBG 3.0 lands in ComfyUI, HyperFrames starts a YouTube channel, and Creatify launches Max
Matting was the theme of today's official posts. LTX ran its Alpha Gen against two other tools on the same footage, and ComfyUI added Bria's new background remover. HyperFrames launched a weekly YouTube show, Creatify introduced an always-on ad agent, and Higgsfield's $1M contest closes Nov 26.
- Stability's image and 3D APIs move to Comfy by Dec 10, Higgsfield opens a $1M Talent Contest, and HyperFrames 0.9.41
If a pipeline of yours calls Stability's image or 3D API, it has a deadline: those endpoints move to Comfy on Dec 10. Higgsfield's new $1M contest wants 3 to 7 minute films by Nov 26. HyperFrames 0.9.41 fixes fast capture on Chrome 157, which had broken some Windows exports.
- Seedance 2.5 Flash: ByteDance's faster, cheaper Seedance tier is live in apps now, with the API on Nov 15
ByteDance has added a Flash tier under Seedance 2.5. BytePlus says it gets close to flagship 2.5 quality at nearly twice the speed and about 34% lower cost per second at 720p. It tops out at 720p, keeps 30-second clips and multi-reference input, and is already live in Higgsfield, CapCut and Lovart. The ModelArk API opened on Nov 15; API notes below.
- #OpenSourceHiggsfield winners: Panorama Stickers, Blocksfield, Imagination Studio and Paint a Plate, plus 10 open builds worth a look
Comfy announced the #OpenSourceHiggsfield winners on Nov 10, as scheduled: more than 300 builds from 45+ countries, all open source. Best Overall went to nomadoor's ComfyUI Panorama Stickers. Below is what each winner does, plus the honorable mentions that matter most if you make video.
- Claude Fable 5.2 is out: what it means for code-made video, motion graphics and Blender work
Anthropic released Claude Fable 5.2 on Nov 9 for all paid plans and the API (claude-fable-5-2). Within hours, the people who make video with code were posting motion graphics, HyperFrames edits and Blender scenes made with it, and Higgsfield put it behind a 3-day free trial of its MCP. Here is what changed and what it costs.
- Higgsfield Miracle: vectorize a finished clip into editable layers for pixel-level post
On Nov 6, Higgsfield introduced Miracle: proprietary post-production that, per their post, vectorizes any video into layers so you can do localized, pixel-level edits in real time with world knowledge baked in. Private beta for select testers now; they say it is coming to Higgsfield MCP so Claude can call it.
- Freefield: an open-weights Higgsfield-style studio on ComfyUI (120 apps, Modal or your GPU)
Freefield rebuilds a Higgsfield-like image/video/VFX/audio studio as ComfyUI workflows with open weights only: each app is a folder with an app.json and an API-format graph. The README lists about 120 apps, lab GPU runs with time and peak VRAM, and a path to run on Modal or on your own ComfyUI. Around 973 GitHub stars as of this morning.
- #OpenSourceHiggsfield closes: five last-hour ComfyUI builds
Entries for ComfyUI's #OpenSourceHiggsfield challenge closed at 9 AM PT on Nov 3, and the hashtag filled with last-minute submissions. Winners are due Nov 10. These five stood out for working video makers: a 3D previs tool, a kinetic-type engine, a MiniMax H3 film studio, a song-sectioned music-video tool and a take-based shot manager.
- #OpenSourceHiggsfield runs to Nov 3, winners Nov 10: four LTX builds to know
Comfy pushed the #OpenSourceHiggsfield deadline to Nov 3 at 9 AM PT and its challenge page now lists winners on Nov 10, not Nov 6. Over the weekend LTX picked out four entries built on LTX-2.5. Here's what changed and what each build does.
- Body Double: recast the performer in a take with open weights in ComfyUI
One of the last #OpenSourceHiggsfield entries, and the one that drew the loudest reaction: Body Double swaps the person in a real take for a new character while the motion, camera, set and original audio stay. Here's how it works, what it needs, and who it's for.
- #OpenSourceHiggsfield final day: six open studios to try
Comfy's open rebuild challenge closes Friday, Oct 30 at 10 AM MDT, and the last 36 hours brought the most complete entries yet. Here are the six worth opening, what each needs to run, and the licences to check.
- Higgsfield sends Comfy a cease and desist; the challenge stays up
On the eve of the deadline, Higgsfield's lawyers asked Comfy to drop the Higgsfield name from its open-rebuild challenge. Comfy's CEO posted the letter and said no. Here's what each side says and what it means if you entered.
- OPENjutsu: Comfy open-sources a character-swap app on MiniMax H3, and a fully local fork follows within hours
Comfy published an MIT-licensed, open take on the 'swap the person in a clip' trick that Higgsfield's Genjutsu made popular. It runs on MiniMax H3 and SAM 3.1. A community fork already runs it entirely on a 16 GB card.
- Henge: an open studio for H3 character swap, motion transfer and head swap, plus Higgsfield open-sources its 'Inside AI' short
One day after Comfy's OPENjutsu, LoRA author Alisson Anjos released Henge, an MIT app that drives his own MiniMax H3 LoRAs for swaps, motion transfer and sharpening, with an MCP server for your agent. The same morning, Higgsfield published every prompt and asset behind its new short film.
- #OpenSourceHiggsfield: Comfy's $25K challenge and the first open rebuilds
Comfy put up $25K for open-source rebuilds of Higgsfield-style apps. Within a day: a camera-move studio, open-weights VFX presets, a script-to-Resolve film studio, and an MCP-only video editor.
- Higgsfield inside Claude: MCP, Soul ID and Katana
One connector URL turns Claude into a front end for Higgsfield's models, characters and audio. Katana adds reference-driven edits.
- A two-layer launch video: code motion over a Seedance plate
Recreate a reference launch video's style for your own product, then layer that motion over cinematic footage built in a strict four-step order.
- Six motion styles clients pay for, according to Higgsfield
A vendor's map of sellable formats, with the workflow tips worth keeping: storyboard first, HTML design sheets, and a credit tally that includes failed takes.
Skills, repos & workflows in the directory (19)
- Paint a Plate ComfyUI
AInVFX's Apache-2.0 ComfyUI node pack for VFX plates: paint on the first frame to erase, add or relight and LTX 2.5 carries it through the shot; paint smoke/fire/fog on blank plates via the ainvfx-fluid IC-LoRA; EXR-in, EXR-out review and export. Open weights only (FLUX 3 Klein, LTX 2.5, SAM 3.1); 32 GB+ VRAM recommended. #OpenSourceHiggsfield Open Weights Only winner.
- ComfyUI Panorama Stickers ComfyUI
nomadoor's MIT node set for placing images, video and 3D in a 360° panorama and shooting any view with keyframed cameras; fix a view with an image model and put it back in place, or re-shoot a shot from a new angle via MoGe 3D. #OpenSourceHiggsfield Best Overall winner.
- Reshoot 4D ComfyUI
itsmetamike's AGPL-3.0 ComfyUI node pack: capture a video of a person in 4D, set a new virtual camera path in a node-panel editor, retake and finish with LTX 2.3, plus lens/DOF/motion-blur passes. Local, open weights only. #OpenSourceHiggsfield honorable mention.
- OneShot MV ComfyUI
VisualFrisson's MIT ComfyUI nodes + studio app: a song plus one line of setting becomes a lip-synced music video (beat/section analysis, invented cast via Krea 2, LTX-2.3 singing clips, SyncNet-checked retakes, auto-edit with drum-driven FX). Single Artist mode only with a consenting artist's photo. #OpenSourceHiggsfield honorable mention.
- Freefield Repo
MIT open-weights Higgsfield-style studio by neuregex on ComfyUI: ~120 image/video/VFX/audio apps as app.json + API workflows (LTX-2.5, MiniMax H3, FLUX 3, etc.), lab runs with time/VRAM, Modal or local GPU. No partner/API nodes.
- Comfy Previs Repo
MIT browser previs tool by sbobyn (#OpenSourceHiggsfield entry): three.js 3D blockouts, cast reference cards, gamepad/iPhone camera, then storyboard stills and AI video (LTX 2.5, Seedance 2.5, Kling O1, Wan VACE) via Comfy Cloud or local ComfyUI, with per-take cost estimates and a Claude MCP connector.
- IV Studio Repo
MIT desktop film studio by Matthew Hollis for MiniMax H3 on your own ComfyUI or Runpod: idea to script, storyboard, shots and finished short (#OpenSourceHiggsfield entry).
- Body Double ComfyUI
lucataco's Apache-2.0 pipeline that recasts the performer in a take as a new character on stock ComfyUI core nodes: SAM 3.1 tracking with re-identification, a follow-cam crop, a FLUX 3 Image Klein first frame and SCAIL-2 in 81-frame segments with QC re-rolls, pasted back into the untouched plate with original audio. About 50 GB GPU memory, 42 GB of models; gated FLUX 3 and SAM licences. Use only footage and likenesses you have rights to.
- OpenCast Studio ComfyUI
Akatz Labs' MIT app for character reference sheets and using those characters in video: Krea 2 OpenCast LoRA portraits, then character swap and motion transfer on Pika H3 Flex via ComfyUI workflows, on your own GPU workstation or one over SSH. An #OpenSourceHiggsfield entry; only swap people with their consent.
- OpenField Repo
wexloops' MIT local Higgsfield-style studio on ComfyUI and open weights: Director shot controls, Scene (local LLM plans and cuts 2-6 shots), Stage (greybox and .glb blocking rendered via the LTX-2.5 layout IC-LoRA), Mirror phone-motion transfer, Reshoot, seam-scored loops, HDR/EXR finishing, 31 MCP tools. NVIDIA 24 GB for video.
- AI Video Studio (Resolve plugin) ComfyUI
Kevin Vandermarliere's paid Resolve plugin: start/end frames from the timeline → local ComfyUI, fal or Higgsfield generations, with a prompt assistant.
- REH (Reverse Engineer Higgsfield) MCP
Rust CLI + local web app + MCP: analyze an AI video (measured shots, cuts, keyframes; model-read prompts labelled as inferred) and write it as a runnable fal.ai flow you can rebuild, verify and batch with your own subjects. MIT.
- seriesmith ComfyUI
Series config + screenplay-style episode scripts in, cut episodes out: every shot compiled to its own ComfyUI job (MiniMax H3, LTX-2, Wan locally or Seedance/Kling/Veo via Comfy Router) with per-shot re-renders. #OpenSourceHiggsfield entry. MIT.
- ReAngle ComfyUI
Re-shoot a clip from a new camera angle with open weights: depth-lift the first frame, draw a camera path in 3D, then depth reprojection guides LTX-2.5 via the Layout-to-Render IC-LoRA. Demo on a 16 GB card. #OpenSourceHiggsfield. Apache-2.0.
- Comfield Repo
#OpenSourceHiggsfield entry: Higgsfield-style image + video studio on the Comfy Developer Platform. Cloud models via Comfy Router or open weights (LTX-2, MiniMax H3, FastH3) on your GPU; 27 camera-motion presets, A–D takes, live pricing. MIT.
- FXjutsu ComfyUI
Open-weights VFX presets on your footage (Vanish, Day→Night, Flood, Alpha Matte, painted-keyframe fire/smoke, restyles, composites) with LTX-2.5 + IC-LoRAs; no partner APIs. #OpenSourceHiggsfield entry.
- Higgsfield MCP MCP
All Higgsfield models, Soul characters, audio, upscaling, Kling Motion Control inside Claude. Uses credits.
- higgsfield-ai/skills Skill
generate / soul / product-photoshoot CLI skills for coding agents.
- Higgsfield Katana Skill
Rebuild a reference edit you own with up to 5 photos of your characters/products.
Pipelines (4)
- Higgsfield MCP + code motion: two-layer cinematic launch · Based on the creator's video
- Higgsfield: consistent fictional spokesperson with lip-sync
- Higgsfield Katana: rebuild a reference edit with your product
- Higgsfield MCP in Claude: launch, hypermotion and explainer formats · Based on the creator's video