`Pixelle-Video`: open-source pipeline for one-prompt short video production

Type one topic and it writes the script, generates visuals, adds TTS, BGM, and renders the final cut. The interesting part is the modular ComfyUI pipeline, so it can become a reusable content factory, not just a demo app.

[ KEY POINTS ]

A single prompt covers script writing, image/video generation, voiceover, background music, and final composition; it compresses the usual short-form workflow into one pass.
Built around ComfyUI, it supports swapping pieces like FLUX, ChatTTS, GPT, Qwen, DeepSeek, and Ollama; the lock-in is lower than most hosted tools.
Recent additions include digital avatar talking-heads, image-to-video, motion transfer, multilingual TTS voices, batch task creation, and history pages; it is moving toward an ops-ready pipeline.
Windows gets a bundled package with no manual Python or ffmpeg setup, while macOS/Linux can install from source; that lowers trial friction for fast content experiments.

Originalgithub.com/AIDC-AI/Pixelle-VideoRead original →

// related

#0001
#0001Generative media GeekNews3 days ago
`SANA-WM`, a 2.6B open-source world model for 1-minute 720p video
50radar
SANA-WMOpen-source world model — generates long video from image and camera path
A single image plus a 6-DoF camera path can produce controlled long video on one GPU. Useful signal for product mockups and scene previews, but still closer to R&D than a plug-and-play SaaS feature.
- Input is one image + 6-DoF camera trajectory, so the value is controlled scene movement rather than text-to-video prompting.
- Hybrid Linear Diffusion Transformer mixes frame-level Gated DeltaNet with periodic softmax to keep long rollouts coherent.
- Single-GPU 720p 1-minute generation lowers experiment cost, but integration still depends on weights, license, and inference setup.
Source: news.hada.io/topic?id=29572Read original →
FIG-0011:1
50radar
FIG-0011:1
#0002
#0002Generative media GeekNews5 days ago
`Supertonic 3` launches ultra-light on-device TTS with 31 languages and emotion tags
60radar
Supertonic 3On-device TTS engine — multilingual with emotion tags
A small-footprint TTS now handles expressive cues like laugh and scream, while improving pronunciation and voice cloning. Strong fit for offline narration, in-app voice UX, and cost-sensitive shipping.
- Supports 31 languages including Korean, which lowers the friction for multilingual voice features without a cloud dependency.
- Adds 10 emotion tags such as laugh, breath, and scream, so scripted dialogue can sound less flat with simple text markup.
- Pronunciation accuracy improved, and repetition or omission failures were reduced; this matters more than flashy demos in production TTS.
- Voice cloning quality also improved, making it more usable for character voices, guided audio, or branded app narration on-device.
Source: news.hada.io/topic?id=29522Read original →
FIG-0021:1
60radar
FIG-0021:1
#0003
#0003Generative media together_ai6 days ago
`Violin`: open-source AI video translation stack
50radar
ViolinOpen-source video translation tool — unifies `ASR`, translation, and `TTS`
An end-to-end stack for multilingual video localization, not just a demo. Useful when you need ASR + translation + TTS without stitching vendors together.
- Combines speech recognition, LLM translation, and text-to-speech in one flow, reducing glue code for video localization.
- Being open-source matters more than model novelty here: you can inspect, swap, and self-host parts of the pipeline.
- Best fit is repurposing existing video assets across languages; less compelling if you only need subtitles or basic dubbing.
Source: www.together.ai/blog/violin-open-source-translation-skilRead original →
FIG-0031:1
50radar
FIG-0031:1

`Pixelle-Video`: open-source pipeline for one-prompt short video production

// related

`SANA-WM`, a 2.6B open-source world model for 1-minute 720p video

`Supertonic 3` launches ultra-light on-device TTS with 31 languages and emotion tags

`Violin`: open-source AI video translation stack