🎨
Creative & Media
Design assets, video, audio
9
Drops
Sort:
9 results1 filters active
Creative & Media
Subcategory
Subcategory
Meshy added a textureresolution parameter for 2K, 4K, and 8K output across its 3D generation and retexture APIs, while keeping hdtexture only as a compatibility alias. Meshy's July 2026 API changelog adds a practical migration point for teams generating higher-resolution 3D assets: use the new textureresolution parameter instead of relying on the older hdtexture boolean. The new parameter supports 2k, 4k, and 8k on Image to 3D, Multi-Image to 3D, Text to 3D Refine, and Retexture endpoints. Meshy says 8K base-color generation costs 15 credits, while 2K and 4K remain 10 credits. At 8K, PBR maps are generated at 4K and no emission map is produced, so pipelines that expect a full PBR bundle should check output fields before swapping defaults. Use this as a quick API cleanup item if your scripts still send hdtexture: true. Meshy still honors it as equivalent to textureresolution: "4k", but the new parameter is clearer, supports 8K explicitly, and makes pricing behavior easier to review before batch generation.
Free
Review open
Text: AI-generated
AI-generated · Automatically published by LinkLoot. ElevenLabs added Music Finetunes API endpoints for creating, listing, checking, updating, and deleting custom music finetunes. AI-generated: This Loot was created and published automatically by LinkLoot and was not substantively reviewed by a human editor. ElevenLabs now exposes Music Finetunes through its API, which makes this useful for teams building repeatable music-generation workflows rather than one-off prompts. The July 20 changelog says the new API can create a finetune from uploaded audio, list accessible finetunes, retrieve training status, update metadata and visibility, and delete a finetune. Music generation SDK methods now expose finetuneid, so an app can route future compositions through a specific trained style or catalog. Use it when you need controlled brand music, recurring creator formats, or internal audio experiments where the same reference material should drive multiple generations. Check rights on the uploaded audio first, keep training sets documented, and treat visibility settings as part of the release checklist. How to evaluate it: Read the July 20 changelog to confirm the endpoints and SDK support. Check the Create Music Finetune reference for required fields such as name and primarygenre. Start with a small, rights-cleared audio set and verify training status before using finetuneid in production generation calls.
Free
Review open
Palmier Pro is a free macOS video editor with an open-source timeline, MCP support for coding agents, and paid generative AI features for creators who want agents inside the edit workflow. What it is Palmier Pro is a macOS video editor aimed at creators who want a conventional timeline plus an AI-agent surface. The public repository describes a Swift-native editor, a local MCP server, and integrations for Claude, Codex, Cursor, and Claude Desktop so an agent can work against the same editing project. The practical hook is the MCP bridge. When the app is open, the project exposes a local MCP endpoint so an agent can connect to the timeline workflow instead of treating the video editor as a black-box GUI task. Why it is useful Use this if you create short-form video, tutorials, product clips, or social edits and want to test what agent-assisted editing feels like without starting from a closed web-only tool. The repository ships a downloadable macOS DMG and the editor can be used without login for normal editing and MCP experiments. The generative AI side is not fully free: the README says video/image generation features require login and subscription. That makes Palmier Pro best viewed as a free editor and agent-integration testbed first, with paid AI generation as an optional layer. Setup surface The latest GitHub release observed for this run is v0.6.14, published on July 22, 2026, with a PalmierPro.dmg asset. The repository metadata reports GPL-3.0 licensing, but the README adds an important caveat: the editor, MCP server, and agent chat are open source, while generative AI processing is closed source. Platform support is narrow. The README states that Palmier Pro requires macOS 26 Tahoe on Apple Silicon, so Windows, Linux, Intel Mac, and older macOS users should skip it for now. Caveats before you try it Do not paste production API keys or private client media into a new editor workflow just because it has an agent interface. Review what the MCP server exposes, use disposable test projects first, and treat any agent/video-generation workflow as a privacy boundary until you know which data stays local and which data goes to external model providers. The install path includes a DMG download and the README also documents agent connection snippets. Review the release asset, permissions, network behavior, and MCP tools before connecting a real coding-agent workspace. Source links Palmier Pro GitHub repository: https://github.com/palmier-io/palmier-pro Palmier Pro v0.6.14 release: https://github.com/palmier-io/palmier-pro/releases/tag/v0.6.14 Show HN discussion: https://news.ycombinator.com/item?id=49022911 Palmier website: https://palmier.io
Free
Review open
A local MCP server that lets compatible AI clients drive Audacity audio-editing workflows through Audacity's scripting interface. Audacity-MCP is a practical bridge for creators who already edit in Audacity and want an MCP-compatible assistant to help with repeatable audio work. The project packages a Python MCP server for Audacity via mod-script-pipe, so the useful angle is not another cloud audio editor; it is local control of an existing desktop editor from clients that can speak MCP. Use it when you want to experiment with assistant-driven podcast cleanup, voiceover editing, transcription labels, export steps, or mastering prep while keeping the audio workflow anchored in Audacity. The PyPI package currently lists audacity-mcp as a beta Python package for AI-driven audio editing via mod-script-pipe and requires Python 3.10 or newer. Evaluation notes before using it in production: Treat it as a beta tool and test on copied project files first. Audacity must support the scripting path the tool relies on; check Audacity's own scripting documentation before setup. Review the install scripts and dependencies before running them on a creator workstation. Do not assume the assistant's audio choices are final; keep human listening and export QA in the loop. Good fit: podcasters, video editors, musicians, and automation builders who want to turn repeated Audacity actions into promptable local workflows without uploading raw audio to a hosted editor.
Free
Review open
FableCut is an open-source browser video editor built around a JSON timeline, MCP/REST control, and live reload so coding agents can assemble edits without driving a conventional GUI. FableCut is a small open-source video editor for teams experimenting with agent-driven media workflows. The useful idea is simple: the project timeline lives as JSON, the editor live-reloads when that file changes, and agents can work through MCP or REST instead of trying to click through a traditional nonlinear editor. Use it when you want to prototype short videos, product clips, narrated demos, or social edits where an agent can plan the structure and update the timeline directly. It is especially interesting for creators who already use coding agents and want video editing to become a file-based workflow. What to check Confirm the repo license and setup steps before using it in commercial work. Test with disposable media first, especially if an agent can edit local project files. Check the export path and whether your workflow needs server-side ffmpeg or browser-side rendering. Keep brand assets, client footage, and credentials outside any folder an autonomous agent can modify. Source check Confirmed by the GitHub repository: FableCut describes itself as a zero-dependency browser video editor with a JSON timeline, MCP/REST controls, and a live-reloading UI. Hacker News is useful context for community interest and early limitations, not the primary source.
Free
Review open
AutoRemesher is an MIT-licensed, cross-platform automatic quad remeshing tool for converting high-polygon meshes into cleaner quad-based topology. The July 2026 1.0.0 release adds ready-to-download Windows, Linux, and macOS builds, a command-line mode, and practical controls such as target quads, sharp edge, adaptivity, and smooth normal settings. AutoRemesher is worth saving if you work with dense scans, sculpted meshes, kitbashed models, or experimental 3D assets that need cleaner quad topology before editing, rigging, or downstream optimization. It is a standalone open-source remeshing tool rather than a Blender-only addon, and the current release includes binaries for Windows, Linux, and macOS. What it does AutoRemesher converts high-polygon input meshes into quad-based output. The project README describes it as a cross-platform automatic quad remeshing tool built on Geogram, libigl, isotropic remesher, and related geometry libraries. The 1.0.0 release is especially useful because it moved to an MIT license, added a command-line interface, improved remeshing and quad extraction algorithms, and exposed controls for target quads, adaptivity, sharp edges, edge scaling, and low-poly smooth normals. Why it is useful Free and open source under the MIT license Runs on Windows, macOS, and Linux Provides release binaries, including AppImage and DMG builds Supports GUI use and headless CLI processing Targets practical retopology jobs for dense meshes and 3D scan cleanup Lets you tune the result with target quads and edge/sharpness settings Quick way to evaluate it Download the 1.0.0 build for your platform from GitHub Releases. Run one dense OBJ test mesh through the GUI. Repeat the same file with CLI mode and a fixed --target-quads value. Inspect edge flow, holes, sharp edge preservation, and UV/material needs in your 3D tool. Keep the command settings that produce acceptable topology for your asset type. Practical LinkLoot angle This is a strong utility pick for 3D creators because it can sit between messy source geometry and heavier tools like Blender, Maya, Cinema 4D, or game-engine import pipelines. The CLI mode also makes it interesting for batch cleanup workflows where you want consistent mesh budgets across many assets. The caveat is the usual one for automatic retopology: it can save time, but it does not replace manual edge-flow decisions for animation-critical faces, hands, joints, or hero assets. Treat it as a first-pass topology tool, then do artist review where the model has to deform or render close up. Source check The GitHub repository lists AutoRemesher as an automatic quad remeshing tool with an MIT license, C++ codebase, and nearly 1,900 stars at the time checked. The 1.0.0 release notes confirm the July 2026 release, MIT relicensing, CLI mode, downloadable platform builds, and the new remeshing controls.
Free
Review open
Microsoft TRELLIS.2 is an open-source 4B image-to-3D model for generating textured mesh assets from a single image. Best for 3D artists, game prototypers, and product mockups that need fast GLB-ready starting points. Microsoft TRELLIS.2 is a practical image-to-3D resource: give it a single image, and it can generate a textured 3D asset with PBR material channels. The official project reports about 3 seconds for 512^3 generation on an NVIDIA H100, with larger 1024^3 and 1536^3 modes taking longer. Use it when you need a fast first-pass asset for Blender, Unity, Unreal, product mockups, game prototypes, or 3D ideation. The project centers on O-Voxel, a field-free sparse voxel representation designed to handle arbitrary topology, open surfaces, non-manifold geometry, opacity, roughness, metallic, and base-color material attributes. Evaluate it before production use. The repository notes Linux support, CUDA requirements, and at least 24GB of NVIDIA GPU memory, with A100 and H100 verification. The model card also warns that raw meshes can still have small holes or artifacts and that the base model is not preference-aligned. Treat the output as a strong editable starting point, not a guaranteed final production mesh.
Free
Review open
A premium agent workflow for creating deterministic MP4 videos from plain HTML, CSS, media, and seekable animations.
29
Review open
PersonaLive is an open‑source, CVPR‑2026‑accepted system that animates a single portrait image in real time for live streaming, supporting up to 12 GB VRAM and offering a TensorRT‑accelerated path for roughly 2× speedup. A ready‑made ComfyUI node and a local WebUI (localhost:7860) let creators and developers run the avatar workflow on prosumer GPUs without SaaS lock‑in. Yes — this is Loot-worthy. PersonaLive is not just another talking-head demo. The repo and paper claims point to something materially more useful: real-time portrait animation from a single image, long-duration streaming behavior, and a hardware profile that is actually reachable for prosumers. What is actually backed by sources accepted for CVPR 2026 GitHub repo with roughly 2.9k stars visible in search/results claims 12GB VRAM support for long-video generation explicit TensorRT 2x speedup path in the repo browser/WebUI flow at localhost:7860 community ComfyUI node already shipped Why this is more than hype The value is tangible for three groups: creators who want local avatar animation without SaaS lock-in ComfyUI users who want a ready community wrapper developers testing real-time portrait animation on gaming-class GPUs
Free
AI review 65
Blog
Articles in Kreativ & Medien
8/2/20264 min
xAI adds reference-guided 1080p video generation to Grok Imagine
KI-generiert / AI-generated · Ohne substanzielle menschliche Prüfung. xAI updated Grok Imagine Video 1.5 with text-to-video, multi-image references, native 1080p output, and API access, giving creators and developers more control over character and scene consistency.
7/30/20263 min
Google launches Lyria 3.5 for song generation in Flow Music
Google's new Lyria 3.5 music model is rolling out in Flow Music with stronger vocals, lyrics, melody quality, tempo control, and track-duration controls.
7/22/20264 min
Qwen-Image-3.0 launches with long-prompt image generation
Alibaba's Qwen team has announced Qwen-Image-3.0, a new image model focused on dense layouts, small text, multilingual rendering, and design-style outputs.
7/20/20264 min
HeyGen sets October deadline for API v1 and v2 migrations
HeyGen now lists October 31, 2026 as the support deadline for its v1 and v2 APIs, with all traffic expected to move to v3 from November 1 and several newer video, avatar, batch, webhook, and agent features already v3-only.