Z Image Turbo
🖼
1.41k
Generate stunning images from text descriptions in seconds
tio
timtx
AI & ML interests
None yet
Recent Activity
liked
a Space
4 days ago
mrfakename/Z-Image-Turbo
liked
a Space
8 days ago
Qwen/Qwen-Image-2512
liked
a Space
2 months ago
HuggingFaceFW/finewiki-viewer
Organizations
None yet
liked
a
Space
4 days ago
liked
a
Space
8 days ago
liked
a
Space
2 months ago
liked
2
Spaces
3 months ago
liked
2
Spaces
4 months ago
liked
a
Space
5 months ago
liked
6
Spaces
6 months ago
GLM 4.5 Demo (API)
🏃
106
Chat with GLM-4.5 to get answers and reasoning
Higgs Audio Demo
🎤
396
Higgs Audio Demo
Grok 4 Heavy Free
🏢
289
Free Grok 4 heavy
Kontext Relight
💡
288
relight images with Flux Kontext[dev]
Meigen MultiTalk
🎙
269
Audio-Driven Multi-Person Conversational Video Generation
FLUX.1 Kontext
⚡
1.54k
Kontext image editing on FLUX[dev]
[MODELS] Discussion
❤️
👍
38
800
#372 opened almost 2 years ago
by
victor
liked
2
Spaces
8 months ago
reacted to
m-ric's
post with 🔥
8 months ago
Post
4537
I've made an open version of Google's NotebookLM, and it shows the superiority of the open source tech task! 💪
The app's workflow is simple. Given a source PDF or URL, it extracts the content from it, then tasks Meta's Llama 3.3-70B with writing the podcast script, with a good prompt crafted by @gabrielchua ("two hosts, with lively discussion, fun notes, insightful question etc.")
Then it hands off the text-to-speech conversion to Kokoro-82M, and there you go, you have two hosts discussion any article.
The generation is nearly instant, because:
> Llama 3.3 70B is running at 1,000 tokens/seconds with Cerebras inference
> The audio is generated in streaming mode by the tiny (yet powerful) Kokoro, generating voices faster than real-time.
And the audio generation runs for free on Zero GPUs, hosted by HF on H200s.
Overall, open source solutions rival the quality of closed-source solutions at close to no cost!
Try it here 👉👉 m-ric/open-notebooklm
The app's workflow is simple. Given a source PDF or URL, it extracts the content from it, then tasks Meta's Llama 3.3-70B with writing the podcast script, with a good prompt crafted by @gabrielchua ("two hosts, with lively discussion, fun notes, insightful question etc.")
Then it hands off the text-to-speech conversion to Kokoro-82M, and there you go, you have two hosts discussion any article.
The generation is nearly instant, because:
> Llama 3.3 70B is running at 1,000 tokens/seconds with Cerebras inference
> The audio is generated in streaming mode by the tiny (yet powerful) Kokoro, generating voices faster than real-time.
And the audio generation runs for free on Zero GPUs, hosted by HF on H200s.
Overall, open source solutions rival the quality of closed-source solutions at close to no cost!
Try it here 👉👉 m-ric/open-notebooklm
- 3 replies
liked
a
Space
8 months ago
liked
a
Space
9 months ago