Remote VAEs for decoding with Inference Endpoints 🤗

Published February 24, 2025

When operating with latent-space diffusion models for high-resolution image and video synthesis, the VAE decoder can consume quite a bit more memory. This makes it hard for the users to run these models on consumer GPUs without going through latency sacrifices and others alike.

For example, with offloading, there is a device transfer overhead, causing delays in the overall inference latency. Tiling is another solution that lets us operate on so-called “tiles” of inputs. However, it can have a negative impact on the quality of the final image.

Therefore, we want to pilot an idea with the community — delegating the decoding process to a remote endpoint.

No data is stored or tracked, and code is open source. We made some changes to huggingface-inference-toolkit and use custom handlers.

This experimental feature is developed by Diffusers 🧨

Table of contents:

Getting started
- Code
- Basic example
- Options
- Generation
- Queueing
Available VAEs
Advantages of using a remote VAE
Provide feedback

Getting started

Below, we cover three use cases where we think this remote VAE inference would be beneficial.

Code

First, we have created a helper method for interacting with Remote VAEs.

Install diffusers from main to run the code. pip install git+https://github.com/huggingface/diffusers@main

Code

from diffusers.utils.remote_utils import remote_decode

Basic example

Here, we show how to use the remote VAE on random tensors.

Code

image = remote_decode(
    endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
    tensor=torch.randn([1, 4, 64, 64], dtype=torch.float16),
    scaling_factor=0.18215,
)

Usage for Flux is slightly different. Flux latents are packed so we need to send the height and width.

Code

image = remote_decode(
    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud/",
    tensor=torch.randn([1, 4096, 64], dtype=torch.float16),
    height=1024,
    width=1024,
    scaling_factor=0.3611,
    shift_factor=0.1159,
)

Finally, an example for HunyuanVideo.

Code

video = remote_decode(
    endpoint="https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud/",
    tensor=torch.randn([1, 16, 3, 40, 64], dtype=torch.float16),
    output_type="mp4",
)
with open("video.mp4", "wb") as f:
    f.write(video)

Generation

But we want to use the VAE on an actual pipeline to get an actual image, not random noise. The example below shows how to do it with SD v1.5.

Code

from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    torch_dtype=torch.float16,
    variant="fp16",
    vae=None,
).to("cuda")

prompt = "Strawberry ice cream, in a stylish modern glass, coconut, splashing milk cream and honey, in a gradient purple background, fluid motion, dynamic movement, cinematic lighting, Mysterious"

latent = pipe(
    prompt=prompt,
    output_type="latent",
).images
image = remote_decode(
    endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
    tensor=latent,
    scaling_factor=0.18215,
)
image.save("test.jpg")

Here’s another example with Flux.

Code

from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-schnell",
    torch_dtype=torch.bfloat16,
    vae=None,
).to("cuda")

prompt = "Strawberry ice cream, in a stylish modern glass, coconut, splashing milk cream and honey, in a gradient purple background, fluid motion, dynamic movement, cinematic lighting, Mysterious"

latent = pipe(
    prompt=prompt,
    guidance_scale=0.0,
    num_inference_steps=4,
    output_type="latent",
).images
image = remote_decode(
    endpoint="https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud/",
    tensor=latent,
    height=1024,
    width=1024,
    scaling_factor=0.3611,
    shift_factor=0.1159,
)
image.save("test.jpg")

Here’s an example with HunyuanVideo.

Code

from diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel

model_id = "hunyuanvideo-community/HunyuanVideo"
transformer = HunyuanVideoTransformer3DModel.from_pretrained(
    model_id, subfolder="transformer", torch_dtype=torch.bfloat16
)
pipe = HunyuanVideoPipeline.from_pretrained(
    model_id, transformer=transformer, vae=None, torch_dtype=torch.float16
).to("cuda")

latent = pipe(
    prompt="A cat walks on the grass, realistic",
    height=320,
    width=512,
    num_frames=61,
    num_inference_steps=30,
    output_type="latent",
).frames

video = remote_decode(
    endpoint="https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud/",
    tensor=latent,
    output_type="mp4",
)

if isinstance(video, bytes):
    with open("video.mp4", "wb") as f:
        f.write(video)

Queueing

One of the great benefits of using a remote VAE is that we can queue multiple generation requests. While the current latent is being processed for decoding, we can already queue another one. This helps improve concurrency.

Code

import queue
import threading
from IPython.display import display
from diffusers import StableDiffusionPipeline

def decode_worker(q: queue.Queue):
    while True:
        item = q.get()
        if item is None:
            break
        image = remote_decode(
            endpoint="https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud/",
            tensor=item,
            scaling_factor=0.18215,
        )
        display(image)
        q.task_done()

q = queue.Queue()
thread = threading.Thread(target=decode_worker, args=(q,), daemon=True)
thread.start()

def decode(latent: torch.Tensor):
    q.put(latent)

prompts = [
    "Blueberry ice cream, in a stylish modern glass , ice cubes, nuts, mint leaves, splashing milk cream, in a gradient purple background, fluid motion, dynamic movement, cinematic lighting, Mysterious",
    "Lemonade in a glass, mint leaves, in an aqua and white background, flowers, ice cubes, halo, fluid motion, dynamic movement, soft lighting, digital painting, rule of thirds composition, Art by Greg rutkowski, Coby whitmore",
    "Comic book art, beautiful, vintage, pastel neon colors, extremely detailed pupils, delicate features, light on face, slight smile, Artgerm, Mary Blair, Edmund Dulac, long dark locks, bangs, glowing, fashionable style, fairytale ambience, hot pink.",
    "Masterpiece, vanilla cone ice cream garnished with chocolate syrup, crushed nuts, choco flakes, in a brown background, gold, cinematic lighting, Art by WLOP",
    "A bowl of milk, falling cornflakes, berries, blueberries, in a white background, soft lighting, intricate details, rule of thirds, octane render, volumetric lighting",
    "Cold Coffee with cream, crushed almonds, in a glass, choco flakes, ice cubes, wet, in a wooden background, cinematic lighting, hyper realistic painting, art by Carne Griffiths, octane render, volumetric lighting, fluid motion, dynamic movement, muted colors,",
]

pipe = StableDiffusionPipeline.from_pretrained(
    "Lykon/dreamshaper-8",
    torch_dtype=torch.float16,
    vae=None,
).to("cuda")

pipe.unet = pipe.unet.to(memory_format=torch.channels_last)
pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)

_ = pipe(
    prompt=prompts[0],
    output_type="latent",
)

for prompt in prompts:
    latent = pipe(
        prompt=prompt,
        output_type="latent",
    ).images
    decode(latent)

q.put(None)
thread.join()

Available VAEs

	Endpoint	Model
Stable Diffusion v1	https://q1bj3bpq6kzilnsu.us-east-1.aws.endpoints.huggingface.cloud	`stabilityai/sd-vae-ft-mse`
Stable Diffusion XL	https://x2dmsqunjd6k9prw.us-east-1.aws.endpoints.huggingface.cloud	`madebyollin/sdxl-vae-fp16-fix`
Flux	https://whhx50ex1aryqvw6.us-east-1.aws.endpoints.huggingface.cloud	`black-forest-labs/FLUX.1-schnell`
HunyuanVideo	https://o7ywnmrahorts457.us-east-1.aws.endpoints.huggingface.cloud	`hunyuanvideo-community/HunyuanVideo`

Advantages of using a remote VAE

These tables demonstrate the VRAM requirements with different GPUs. Memory usage % determines whether users of a certain GPU will need to offload. Offload times vary with CPU, RAM and HDD/NVMe. Tiled decoding increases inference time.

SD v1.5

GPU	Resolution	Time (seconds)	Memory (%)	Tiled Time (secs)	Tiled Memory (%)
NVIDIA GeForce RTX 4090	512x512	0.031	5.60%	0.031 (0%)	5.60%
NVIDIA GeForce RTX 4090	1024x1024	0.148	20.00%	0.301 (+103%)	5.60%
NVIDIA GeForce RTX 4080	512x512	0.05	8.40%	0.050 (0%)	8.40%
NVIDIA GeForce RTX 4080	1024x1024	0.224	30.00%	0.356 (+59%)	8.40%
NVIDIA GeForce RTX 4070 Ti	512x512	0.066	11.30%	0.066 (0%)	11.30%
NVIDIA GeForce RTX 4070 Ti	1024x1024	0.284	40.50%	0.454 (+60%)	11.40%
NVIDIA GeForce RTX 3090	512x512	0.062	5.20%	0.062 (0%)	5.20%
NVIDIA GeForce RTX 3090	1024x1024	0.253	18.50%	0.464 (+83%)	5.20%
NVIDIA GeForce RTX 3080	512x512	0.07	12.80%	0.070 (0%)	12.80%
NVIDIA GeForce RTX 3080	1024x1024	0.286	45.30%	0.466 (+63%)	12.90%
NVIDIA GeForce RTX 3070	512x512	0.102	15.90%	0.102 (0%)	15.90%
NVIDIA GeForce RTX 3070	1024x1024	0.421	56.30%	0.746 (+77%)	16.00%

SDXL

GPU	Resolution	Time (seconds)	Memory Consumed (%)	Tiled Time (seconds)	Tiled Memory (%)
NVIDIA GeForce RTX 4090	512x512	0.057	10.00%	0.057 (0%)	10.00%
NVIDIA GeForce RTX 4090	1024x1024	0.256	35.50%	0.257 (+0.4%)	35.50%
NVIDIA GeForce RTX 4080	512x512	0.092	15.00%	0.092 (0%)	15.00%
NVIDIA GeForce RTX 4080	1024x1024	0.406	53.30%	0.406 (0%)	53.30%
NVIDIA GeForce RTX 4070 Ti	512x512	0.121	20.20%	0.120 (-0.8%)	20.20%
NVIDIA GeForce RTX 4070 Ti	1024x1024	0.519	72.00%	0.519 (0%)	72.00%
NVIDIA GeForce RTX 3090	512x512	0.107	10.50%	0.107 (0%)	10.50%
NVIDIA GeForce RTX 3090	1024x1024	0.459	38.00%	0.460 (+0.2%)	38.00%
NVIDIA GeForce RTX 3080	512x512	0.121	25.60%	0.121 (0%)	25.60%
NVIDIA GeForce RTX 3080	1024x1024	0.524	93.00%	0.524 (0%)	93.00%
NVIDIA GeForce RTX 3070	512x512	0.183	31.80%	0.183 (0%)	31.80%
NVIDIA GeForce RTX 3070	1024x1024	0.794	96.40%	0.794 (0%)	96.40%

Provide feedback

If you like the idea and feature, please help us with your feedback on how we can make this better and whether you’d be interested in having this kind of feature more natively integrated into the Hugging Face ecosystem. If this pilot goes well, we plan on creating optimized VAE endpoints for more models, including the ones that can generate high-resolution videos!

Steps:

Open an issue on Diffusers through this link.
Answer the questions and provide any extra info you want.
Hit submit!

The AI tools for Art Newsletter - Issue 1

By January 31, 2025 • 70

State of open video generation models in Diffusers

By January 27, 2025 • 50

Community

@hlky\n\t can comment more on the offloading time but you can almost take our word for granted that offloading does incur quite a bit of device transfer overhead, introducing further latency. This is where remote VAE decoding would be helpful.

\n","updatedAt":"2025-02-25T13:34:18.261Z","author":{"_id":"5f7fbd813e94f16a85448745","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg","fullname":"Sayak Paul","name":"sayakpaul","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":585}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9485061764717102},"editors":["sayakpaul"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg"],"reactions":[],"isReport":false,"parentCommentId":"67bc5ac4f9641a9ff16e9fcd"}}]},{"id":"67bc85db98d639deeaab1ab6","author":{"_id":"643ead1f4fa8bccfd721ea2b","avatarUrl":"/avatars/b34c1d0bdd87b3a091b730b7e9a4f628.svg","fullname":"RAHUL YASHWANTKUMAR GUPTA","name":"ryg81","type":"user","isPro":false,"isHf":false,"isMod":false,"followerCount":1},"createdAt":"2025-02-24T14:44:43.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Do we need Pro account for this?","html":"

Do we need Pro account for this?

\n","updatedAt":"2025-02-24T14:44:43.687Z","author":{"_id":"643ead1f4fa8bccfd721ea2b","avatarUrl":"/avatars/b34c1d0bdd87b3a091b730b7e9a4f628.svg","fullname":"RAHUL YASHWANTKUMAR GUPTA","name":"ryg81","type":"user","isPro":false,"isHf":false,"isMod":false,"followerCount":1}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9459798336029053},"editors":["ryg81"],"editorAvatarUrls":["/avatars/b34c1d0bdd87b3a091b730b7e9a4f628.svg"],"reactions":[],"isReport":false}},{"id":"67bc88f78de2585e8751dffe","author":{"_id":"5f7fbd813e94f16a85448745","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg","fullname":"Sayak Paul","name":"sayakpaul","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":585},"createdAt":"2025-02-24T14:57:59.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"No. ","html":"

No.

\n","updatedAt":"2025-02-24T14:57:59.409Z","author":{"_id":"5f7fbd813e94f16a85448745","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg","fullname":"Sayak Paul","name":"sayakpaul","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":585}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9973126649856567},"editors":["sayakpaul"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg"],"reactions":[],"isReport":false}},{"id":"67bd9e9e5cb11ce46a9251f2","author":{"_id":"638b30fbd274cbbad27ef26a","avatarUrl":"/avatars/bd8ef2fe46c5fded1fc0e15e2c4949bf.svg","fullname":"fkun","name":"freykun","type":"user","isPro":false,"isHf":false,"isMod":false},"createdAt":"2025-02-25T10:42:38.000Z","type":"comment","data":{"edited":true,"hidden":false,"latest":{"raw":"Hello there.\nVery nice implementation, works flawlessly, 2-4 seconds to decode, depending on image size.\n\nSimple question, is there a possibility to create a local endpoint on other machine (not HF) and use it as vae-decode machine?\n\nSo a Comfy Ui implementation for example.\n","html":"

Hello there.
Very nice implementation, works flawlessly, 2-4 seconds to decode, depending on image size.

Simple question, is there a possibility to create a local endpoint on other machine (not HF) and use it as vae-decode machine?

So a Comfy Ui implementation for example.

\n","updatedAt":"2025-02-25T10:43:50.017Z","author":{"_id":"638b30fbd274cbbad27ef26a","avatarUrl":"/avatars/bd8ef2fe46c5fded1fc0e15e2c4949bf.svg","fullname":"fkun","name":"freykun","type":"user","isPro":false,"isHf":false,"isMod":false}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.8189413547515869},"editors":["freykun"],"editorAvatarUrls":["/avatars/bd8ef2fe46c5fded1fc0e15e2c4949bf.svg"],"reactions":[],"isReport":false}},{"id":"67bd9fccbad54c0589983878","author":{"_id":"5f7fbd813e94f16a85448745","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg","fullname":"Sayak Paul","name":"sayakpaul","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":585},"createdAt":"2025-02-25T10:47:40.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Comfy implementation: https://github.com/kijai/ComfyUI-HFRemoteVae\n\nYou can host the endpoint on a local machine and use it as is as shown in the blog post if the input and output schemas match.","html":"

Comfy implementation: https://github.com/kijai/ComfyUI-HFRemoteVae

You can host the endpoint on a local machine and use it as is as shown in the blog post if the input and output schemas match.

\n","updatedAt":"2025-02-25T10:47:40.641Z","author":{"_id":"5f7fbd813e94f16a85448745","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg","fullname":"Sayak Paul","name":"sayakpaul","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":585}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7996358275413513},"editors":["sayakpaul"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg"],"reactions":[],"isReport":false},"replies":[{"id":"67bda2a54475a18d5411218e","author":{"_id":"638b30fbd274cbbad27ef26a","avatarUrl":"/avatars/bd8ef2fe46c5fded1fc0e15e2c4949bf.svg","fullname":"fkun","name":"freykun","type":"user","isPro":false,"isHf":false,"isMod":false},"createdAt":"2025-02-25T10:59:49.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Alright, I'll give it another read. \nThank you.\n","html":"

Alright, I'll give it another read.
Thank you.

\n","updatedAt":"2025-02-25T10:59:49.246Z","author":{"_id":"638b30fbd274cbbad27ef26a","avatarUrl":"/avatars/bd8ef2fe46c5fded1fc0e15e2c4949bf.svg","fullname":"fkun","name":"freykun","type":"user","isPro":false,"isHf":false,"isMod":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9753603935241699},"editors":["freykun"],"editorAvatarUrls":["/avatars/bd8ef2fe46c5fded1fc0e15e2c4949bf.svg"],"reactions":[{"reaction":"👍","users":["sayakpaul"],"count":1}],"isReport":false,"parentCommentId":"67bd9fccbad54c0589983878"}}]},{"id":"67bdd1bc30eecba21c77b85a","author":{"_id":"63ca214abedad7e2bf1d1517","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png","fullname":"Xuan-Son Nguyen","name":"ngxson","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":158},"createdAt":"2025-02-25T14:20:44.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"📻 🎙️ Hey, I generated an **AI podcast** about this blog post, check it out!\n\n

\n\n*This podcast is generated via [ngxson/kokoro-podcast-generator](https://huggingface.co/spaces/ngxson/kokoro-podcast-generator), using [DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1) and [Kokoro-TTS](https://huggingface.co/hexgrad/Kokoro-82M).*","html":"

📻 🎙️ Hey, I generated an AI podcast about this blog post, check it out!

This podcast is generated via ngxson/kokoro-podcast-generator, using DeepSeek-R1 and Kokoro-TTS.

\n","updatedAt":"2025-02-25T14:20:44.332Z","author":{"_id":"63ca214abedad7e2bf1d1517","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png","fullname":"Xuan-Son Nguyen","name":"ngxson","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":158}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6395361423492432},"editors":["ngxson"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png"],"reactions":[{"reaction":"🤝","users":["ariG23498","muhtasham"],"count":2},{"reaction":"🤯","users":["ariG23498","muhtasham"],"count":2}],"isReport":false},"replies":[{"id":"67bddb49cfa37b39f2ab49b7","author":{"_id":"5f7fbd813e94f16a85448745","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg","fullname":"Sayak Paul","name":"sayakpaul","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":585},"createdAt":"2025-02-25T15:01:29.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"No audio.","html":"

No audio.

\n","updatedAt":"2025-02-25T15:01:29.243Z","author":{"_id":"5f7fbd813e94f16a85448745","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg","fullname":"Sayak Paul","name":"sayakpaul","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":585}},"numEdits":0,"identifiedLanguage":{"language":"la","probability":0.2297130674123764},"editors":["sayakpaul"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg"],"reactions":[],"isReport":false,"parentCommentId":"67bdd1bc30eecba21c77b85a"}},{"id":"67bde04e354206fc3b918f4f","author":{"_id":"63ca214abedad7e2bf1d1517","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png","fullname":"Xuan-Son Nguyen","name":"ngxson","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":158},"createdAt":"2025-02-25T15:22:54.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Still fine for me, maybe check your speaker =)","html":"

Still fine for me, maybe check your speaker =)

\n","updatedAt":"2025-02-25T15:22:54.152Z","author":{"_id":"63ca214abedad7e2bf1d1517","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png","fullname":"Xuan-Son Nguyen","name":"ngxson","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":158}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9694971442222595},"editors":["ngxson"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png"],"reactions":[],"isReport":false,"parentCommentId":"67bdd1bc30eecba21c77b85a"}},{"id":"67bedfcb4e0e135c3079b176","author":{"_id":"5f7fbd813e94f16a85448745","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg","fullname":"Sayak Paul","name":"sayakpaul","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":585},"createdAt":"2025-02-26T09:32:59.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Again did still no luck. Downloaded it and it worked fine. Very fine work. Do you have a tweet?","html":"

Again did still no luck. Downloaded it and it worked fine. Very fine work. Do you have a tweet?

\n","updatedAt":"2025-02-26T09:32:59.813Z","author":{"_id":"5f7fbd813e94f16a85448745","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg","fullname":"Sayak Paul","name":"sayakpaul","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":585}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9873870611190796},"editors":["sayakpaul"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg"],"reactions":[{"reaction":"❤️","users":["ngxson","muhtasham"],"count":2},{"reaction":"🚀","users":["ngxson"],"count":1}],"isReport":false,"parentCommentId":"67bdd1bc30eecba21c77b85a"}},{"id":"67bee32834176021e0cc51b2","author":{"_id":"608aabf24955d2bfc3cd99c6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/608aabf24955d2bfc3cd99c6/T762Ut0Y-w0sZB2ynvfbJ.jpeg","fullname":"Aritra Roy Gosthipaty","name":"ariG23498","type":"user","isPro":true,"isHf":true,"isMod":false,"followerCount":130},"createdAt":"2025-02-26T09:47:20.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is really nice!","html":"

This is really nice!

\n","updatedAt":"2025-02-26T09:47:20.904Z","author":{"_id":"608aabf24955d2bfc3cd99c6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/608aabf24955d2bfc3cd99c6/T762Ut0Y-w0sZB2ynvfbJ.jpeg","fullname":"Aritra Roy Gosthipaty","name":"ariG23498","type":"user","isPro":true,"isHf":true,"isMod":false,"followerCount":130}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9980546236038208},"editors":["ariG23498"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/608aabf24955d2bfc3cd99c6/T762Ut0Y-w0sZB2ynvfbJ.jpeg"],"reactions":[{"reaction":"❤️","users":["ngxson","muhtasham"],"count":2}],"isReport":false,"parentCommentId":"67bdd1bc30eecba21c77b85a"}},{"id":"67bef7937a424f8216af7d4d","author":{"_id":"63ca214abedad7e2bf1d1517","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png","fullname":"Xuan-Son Nguyen","name":"ngxson","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":158},"createdAt":"2025-02-26T11:14:27.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"@sayakpaul I tweeted about this feature last week when it was initial out. Feel free to also post on your profile ;-)","html":"

\n\n@sayakpaul\n\t I tweeted about this feature last week when it was initial out. Feel free to also post on your profile ;-)

\n","updatedAt":"2025-02-26T11:14:27.660Z","author":{"_id":"63ca214abedad7e2bf1d1517","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png","fullname":"Xuan-Son Nguyen","name":"ngxson","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":158}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.969934344291687},"editors":["ngxson"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png"],"reactions":[],"isReport":false,"parentCommentId":"67bdd1bc30eecba21c77b85a"}},{"id":"67bef7f8d90ae3e50bd0f189","author":{"_id":"63ca214abedad7e2bf1d1517","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png","fullname":"Xuan-Son Nguyen","name":"ngxson","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":158},"createdAt":"2025-02-26T11:16:08.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Btw feel free to let me know if there are any problem with the podcast content - I can tweak the prompt to make it better haha.\n\nThe voice is still quite \"robotic\", but in near future there will be better open-source TTS model!","html":"

Btw feel free to let me know if there are any problem with the podcast content - I can tweak the prompt to make it better haha.

The voice is still quite \"robotic\", but in near future there will be better open-source TTS model!

\n","updatedAt":"2025-02-26T11:16:08.585Z","author":{"_id":"63ca214abedad7e2bf1d1517","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png","fullname":"Xuan-Son Nguyen","name":"ngxson","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":158}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9351606965065002},"editors":["ngxson"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png"],"reactions":[{"reaction":"😎","users":["ariG23498","sayakpaul"],"count":2}],"isReport":false,"parentCommentId":"67bdd1bc30eecba21c77b85a"}},{"id":"67bf00394426925c82c7df1b","author":{"_id":"5f7fbd813e94f16a85448745","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg","fullname":"Sayak Paul","name":"sayakpaul","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":585},"createdAt":"2025-02-26T11:51:21.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"@ngxson if you have the tweet link with the podcast, please post here! This needs to go viral.","html":"

\n\n@ngxson\n\t if you have the tweet link with the podcast, please post here! This needs to go viral.

\n","updatedAt":"2025-02-26T11:51:21.501Z","author":{"_id":"5f7fbd813e94f16a85448745","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg","fullname":"Sayak Paul","name":"sayakpaul","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":585}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.905803918838501},"editors":["sayakpaul"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1649681653581-5f7fbd813e94f16a85448745.jpeg"],"reactions":[],"isReport":false,"parentCommentId":"67bdd1bc30eecba21c77b85a"}},{"id":"67bf2ab723f222a2cc29fe59","author":{"_id":"63ca214abedad7e2bf1d1517","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png","fullname":"Xuan-Son Nguyen","name":"ngxson","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":158},"createdAt":"2025-02-26T14:52:39.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Here you go! I also posted the link to this blog article in the reply: https://x.com/ngxson/status/1894762186544762896","html":"

Here you go! I also posted the link to this blog article in the reply: https://x.com/ngxson/status/1894762186544762896

\n","updatedAt":"2025-02-26T14:52:39.152Z","author":{"_id":"63ca214abedad7e2bf1d1517","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png","fullname":"Xuan-Son Nguyen","name":"ngxson","type":"user","isPro":false,"isHf":true,"isMod":false,"followerCount":158}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8886865377426147},"editors":["ngxson"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674191139776-noauth.png"],"reactions":[{"reaction":"❤️","users":["sayakpaul","muhtasham"],"count":2}],"isReport":false,"parentCommentId":"67bdd1bc30eecba21c77b85a"}}]},{"id":"67bf39fdd067f2e27ea0d715","author":{"_id":"671c7788b91f5a4a2485b8d6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/671c7788b91f5a4a2485b8d6/8-GqEdU2jUQqlAXsuXjpR.png","fullname":"Eramth Ru","name":"eramth","type":"user","isPro":false,"isHf":false,"isMod":false,"followerCount":2},"createdAt":"2025-02-26T15:57:49.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Very nice feature.","html":"

Very nice feature.

\n","updatedAt":"2025-02-26T15:57:49.687Z","author":{"_id":"671c7788b91f5a4a2485b8d6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/671c7788b91f5a4a2485b8d6/8-GqEdU2jUQqlAXsuXjpR.png","fullname":"Eramth Ru","name":"eramth","type":"user","isPro":false,"isHf":false,"isMod":false,"followerCount":2}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7970151305198669},"editors":["eramth"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/671c7788b91f5a4a2485b8d6/8-GqEdU2jUQqlAXsuXjpR.png"],"reactions":[],"isReport":false}},{"id":"67c0ee2e68068db4e796028d","author":{"_id":"63850da6a179f85600595e2a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1669949083086-63850da6a179f85600595e2a.png","fullname":"JTF","name":"DigitalSolomon","type":"user","isPro":false,"isHf":false,"isMod":false},"createdAt":"2025-02-27T22:58:54.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Great work! Just posted a video short to LinkedIn showcasing this. Check it out! https://www.linkedin.com/posts/activity-7301008441123164161-rTau?utm_source=social_share_send&utm_medium=member_desktop_web&rcm=ACoAAAI2QycBC7JU4jV0Vw61G4AWBGaE_MlKUtU","html":"

Great work! Just posted a video short to LinkedIn showcasing this. Check it out! https://www.linkedin.com/posts/activity-7301008441123164161-rTau?utm_source=social_share_send&utm_medium=member_desktop_web&rcm=ACoAAAI2QycBC7JU4jV0Vw61G4AWBGaE_MlKUtU

\n","updatedAt":"2025-02-27T22:58:54.899Z","author":{"_id":"63850da6a179f85600595e2a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1669949083086-63850da6a179f85600595e2a.png","fullname":"JTF","name":"DigitalSolomon","type":"user","isPro":false,"isHf":false,"isMod":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6078242659568787},"editors":["DigitalSolomon"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1669949083086-63850da6a179f85600595e2a.png"],"reactions":[{"reaction":"🚀","users":["ariG23498","sayakpaul"],"count":2}],"isReport":false}}],"status":"open","isReport":false,"pinned":false,"locked":false,"collection":"canonical_blogs"},"contextAuthors":["hlky","sayakpaul"],"primaryEmailConfirmed":false,"discussionRole":0,"acceptLanguages":["en","*"],"withThread":true,"cardDisplay":false}">