UPDATE ! CivitAI added Mochi & Haiper Video on site Generation !
Don't forget all my LTXV, CogVideo & Mochi Video Prompt lists are here:
https://github.com/MushroomFleet/DJZ-Nodes/tree/main/prompts
November Update
Donut-Mochi V8 showcase video:
please comment if we missed your favorite AI video generator!
On Site
These models can now be run right here on CivitAI with BUZZ !
Mochi
Haiper
Workflows
These can be run "at home" with local GPU
XODA-LTXV-Pack
https://civitai.com/models/974859/xoda-ltxv-video-packDonut Mochi **NOVEMBER
https://civitai.com/models/886896/donut-mochi-pack-video-generationCogVideo **NOVEMBER
https://civitai.com/models/734262/cogvideo-packSDV-XT 1.1, animateLCM **JULY
https://civitai.com/models/331664/virgil-sdv-11SDXL Animatediff
https://civitai.com/models/331700/odinson-sdxl-animatediffLooping Motion 2 UPDATE IN JULY!
https://civitai.com/models/410919LOKI Fast Face Swap Pack, Live Portrait & MimicMotion **JULY
https://civitai.com/models/539936/loki-live-portrait-fastest-face-swap-batch-modesNOVA Re-Lighting Tools **JULY
https://civitai.com/models/565597/nova-re-lighting-toolsRotoMaker-Studio, TrioSDXLcnet, MimicMotion, Reactor Faceswap, auto-matte rotoscope tools, automatic output collection by Project Name. (Video2Video) **JULY
https://civitai.com/models/586617/rotomaker-with-rotoscope-tools
Paid Tools
These are often paid services with supercompute in the cloud
Hailuo (minimax model) **NOVEMBER
https://hailuoai.com/videoNoisee.ai AMV generation
https://www.noisee.aitxt2motion
https://www.mootion.com/landingPika.art video generation **NOV
https://pika.art/Eleven Labs Dubbing
https://elevenlabs.io/dubbingD-ID, Virtual Assistant Video
https://studio.d-id.com/Haiper.ai, Video Generation
https://app.haiper.ai/synclabs.so, video AI lipsync
https://synclabs.so/lumalabs.ai, Video Generation JUNE
https://lumalabs.ai/dream-machine/dream-machineRunway.ml, GEN-3 model **NOV
https://app.runwayml.com/video-toolsLTX.studio, Storyboard focused multi-generation service
https://ltx.studio/ **JULY
LTXV
The fastest Local generation model released as of time of writing ( 23rd November 2024). Allows generation of photorealistic videos with Light Tricks LTXV model. My XODA-LTXV workflow pack offers text2video and image2video with prompts/images. I also provided a finetuned LLM PromptGen module for Claude & 110 prompts in 11 lists by category. It can deliver 2 seconds of video in ~8 seconds of generation time, this is the fastest Local GPU video generation model.
Mochi1
Allows generation of photorealistic videos with Mochi1. My Donut-Mochi workflow packs offered text2video and image2video with prompts/images, featured save/load latents and high quality mix of model/clip types to achieve the best outputs. It can run on a 12GB GPU which represents the most accessible video generation option for local GPU owners.
CogVideo
Allows generation of random animation with CogXVideo model. The workflow used text to video with a wrapper from Kijai.
SDV-XT 1.1
Allows generation of random animation with Stable Diffusion Video XT 1.1. The workflow used a single input image with no prompt.
SDXL Animatediff
Used existing SDXL Checkpoints (and lora) with Controlnet and Animatediff XL. The workflow requires a stack of models to run, and take a video input. full details are explained on the workflow page.
Local Above ~~~ Paid below
Noisee Animated Music Video Generation
Takes a song URL, Discord image URL and general style and/or scene by scene prompts. Produces 60 seconds of high quality 1024x576 video (aspect ratio is a parameter)
Mootion Text to Motion
Discord service allows us to select a 3D model from a list, while prompting animation. These animations can be transformed with prompts (and saved for use with animatediff)
Eleven Labs Dubbing Translator
Translate your content across 29 languages in seconds with voice translation, speaker detection, and audio dubbing, could be used as part of a multi stage project, but lip sync is a new service that pops up in an improved form from time to time.
D-ID Virtual Assistants / Agents
Generated Audio and video, lip synced with a personality, programmable with API
Haiper AI
Currently one of the best text2video HD & img2video HD generators out there, for music video creation
SyncLabs
Allows you to redub a video with AI lipsync
LumaLabs
Best known for their motion capture AI, they recently released a groundbreaking text and image to video service.
RunwayML
the original trainers of SD1.5, they have released Gen-3 Video Generation service as of July 2024.
also allows you to redub videos with AI lipsync
LTX Studio
Storyboard based AI video generation, used LLM to expand your prompt and allows later prompting in each scene, many options for soundtrack and speech generation, can output as a finished story.
other methods will be added here soon :) please comment with services we missed.