正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

High fidelity image editing is now in the OpenAI API and ChatGPT! Here's a quick demo I made that focuses on editing faces. It adds mustaches and facial expressions—but preserves all the other details of the face. Notice how my hair, glasses, nose, etc are perfectly maintained.

edwin

24,436 subscribers

41,819 次观看 • 1 年前 •via X (Twitter)

科学技术教育艺术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

We've improved image generation in the API. Editing with faces, logos, and fine-grained details is now much higher fidelity with features preserved. 🔍 Edit specific objects, create marketing assets with your logo, or adjust facial expressions, poses, and outfits on people.

OpenAI Developers

459,742 次观看 • 1 年前

Introducing ChatGPT Images 2.0 A state-of-the-art image model that can take on complex visual tasks and produce precise, immediately usable visuals, with sharper editing, richer layouts, and thinking-level intelligence. Video made with ChatGPT Images

Introducing ChatGPT Images 2.0 A state-of-the-art image model that can take on complex visual tasks and produce precise, immediately usable visuals, with sharper editing, richer layouts, and thinking-level intelligence. Video made with ChatGPT Images

OpenAI

12,891,229 次观看 • 2 个月前

Foxdee expressions demo a few expressions that my OC can make with the rigify facial rig, I have always used the rigify rig but I have never delved into the expressions I could do with it With this I want to start an animation portfolio c: VA and sound editing by Tarooi

Foxdee expressions demo a few expressions that my OC can make with the rigify facial rig, I have always used the rigify rig but I have never delved into the expressions I could do with it With this I want to start an animation portfolio c: VA and sound editing by Tarooi

Foxdee

68,081 次观看 • 1 年前

And here's the bonus! It contains less editing, and some videos that focuses only on the unobstructed view of the maid mommy Rina. That physics glitch is unexpected, but enjoyable nonetheless. #zzzero #ZenlessZoneZero #Alexandrina #AlexandrinaSebastiane #MMD #リョナ #ryona

Sensitive content

And here's the bonus! It contains less editing, and some videos that focuses only on the unobstructed view of the maid mommy Rina. That physics glitch is unexpected, but enjoyable nonetheless. #zzzero #ZenlessZoneZero #Alexandrina #AlexandrinaSebastiane #MMD #リョナ #ryona

RookHMA

27,362 次观看 • 2 年前

These facial animations in Fable are looking really rough if I'm honest. The level of fidelity in the faces themselves is impressive but the NPCs are lacking facial expressions and seem very stiff. Really hoping that by the time the game comes out, the devs manage to fix them

These facial animations in Fable are looking really rough if I'm honest. The level of fidelity in the faces themselves is impressive but the NPCs are lacking facial expressions and seem very stiff. Really hoping that by the time the game comes out, the devs manage to fix them

NikTek

315,400 次观看 • 1 个月前

Repo Prompt is a macOS app I built because I didn't want to change IDEs, and copy pasting changes from Claude and ChatGPT was taking too much of my time Here's a very WIP demo of me editing my website with it. Would love to put it in the hands of more people- Testflight is open!

Repo Prompt is a macOS app I built because I didn't want to change IDEs, and copy pasting changes from Claude and ChatGPT was taking too much of my time Here's a very WIP demo of me editing my website with it. Would love to put it in the hands of more people- Testflight is open!

eric provencher

21,649 次观看 • 1 年前

ChatGPT hasn't been my main chatbot for a long time But Google AI Mode is. You basically have everything in one place: - Nano banana for image gen/editing - Gemini 2.5 Flash and Pro - Voice typing - File handling - Deep research And above all, the best web grounding available (better than ChatGPT, Claude, etc.). Google is the new Google.

ChatGPT hasn't been my main chatbot for a long time But Google AI Mode is. You basically have everything in one place: - Nano banana for image gen/editing - Gemini 2.5 Flash and Pro - Voice typing - File handling - Deep research And above all, the best web grounding available (better than ChatGPT, Claude, etc.). Google is the new Google.

Paul Couvert

71,417 次观看 • 8 个月前

With today's OpenAI image gen updates, I made this demo site that generates cute skeuomorphic images. With the Responses API + gpt-4.1, it supports: – image streaming and a progress bar (via Responses events) – speed/quality toggle – image uploads – image edits

With today's OpenAI image gen updates, I made this demo site that generates cute skeuomorphic images. With the Responses API + gpt-4.1, it supports: – image streaming and a progress bar (via Responses events) – speed/quality toggle – image uploads – image edits

edwin

53,564 次观看 • 1 年前

Here's a demo of the gpt-4-vision API that I built in Bubble in 30 min. It takes a URL, converts it to an image, and sends it through the Vision API to respond with custom landing page optimization suggestions.

Here's a demo of the gpt-4-vision API that I built in Bubble in 30 min. It takes a URL, converts it to an image, and sends it through the Vision API to respond with custom landing page optimization suggestions.

Seth Kramer

953,992 次观看 • 2 年前

Grok Imagine 1.5 is now on Higgsfield. It debuted number one on the Artificial Analysis Image-to-Video leaderboard at 1404 Elo. Preserves detail and lighting fidelity from the input frame. Measurable gains in cloth dynamics, water simulation, hair motion, and glass rendering.

Grok Imagine 1.5 is now on Higgsfield. It debuted number one on the Artificial Analysis Image-to-Video leaderboard at 1404 Elo. Preserves detail and lighting fidelity from the input frame. Measurable gains in cloth dynamics, water simulation, hair motion, and glass rendering.

Higgsfield AI 🧩

63,370 次观看 • 1 个月前

SendAI's Solana MCP is now available in the OpenAI Responses API 🤖 Just plug in the SendAI Remote MCP server and prompt Solana actions in your agentic workflows (Chain-of-Thought) using your own Solana wallet. A quick demo of fetching and buying $SEND on the OpenAI Platform:

SendAI's Solana MCP is now available in the OpenAI Responses API 🤖 Just plug in the SendAI Remote MCP server and prompt Solana actions in your agentic workflows (Chain-of-Thought) using your own Solana wallet. A quick demo of fetching and buying $SEND on the OpenAI Platform:

SendAI

22,961 次观看 • 1 年前

Here's a quick tip for you! 💡Revamp your outdated resources by uploading and editing them in Canva. Check out the full tutorial on how to do it here:

Here's a quick tip for you! 💡Revamp your outdated resources by uploading and editing them in Canva. Check out the full tutorial on how to do it here:

Canva Education

30,111 次观看 • 3 年前

i built a free tool* using the chatgpt api to add a mask to an image so it only modifies the area you select the idea is that in chatgpt it changes the full img, but this focuses the edit not sure it's 100% working tho as some images change a lot still *bring your own key

i built a free tool* using the chatgpt api to add a mask to an image so it only modifies the area you select the idea is that in chatgpt it changes the full img, but this focuses the edit not sure it's 100% working tho as some images change a lot still *bring your own key

Ian Nuttall

22,119 次观看 • 1 年前

To answer all the questions on how this works, the model is actually an image of a plushie that I split into layers and rigged like normal from there in Live2D. Here's a quick speed paint reference to show how the layers were made in CSP using photo manip strats 🧡

To answer all the questions on how this works, the model is actually an image of a plushie that I split into layers and rigged like normal from there in Live2D. Here's a quick speed paint reference to show how the layers were made in CSP using photo manip strats 🧡

Clover 🍀🐮

95,121 次观看 • 1 年前

I spent the last 48 hours building on top of the new ChatGPT API. You can now create a custom ChatGPT from the content of your website using You can then take that chatbot and add it to any website as a chat bubble. Pinecone OpenAI

I spent the last 48 hours building on top of the new ChatGPT API. You can now create a custom ChatGPT from the content of your website using You can then take that chatbot and add it to any website as a chat bubble. Pinecone OpenAI

Yasser

929,920 次观看 • 3 年前

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

AK

16,062 次观看 • 1 年前

Sam Altman was also surprised that no one built ChatGPT before OpenAI: "we had the model for ChatGPT in the API for ~10 months before we made ChatGPT .. I sort of thought someone (else) was gonna just build it" (reminder: there are *many* similarly unbuilt products right now)

Sam Altman was also surprised that no one built ChatGPT before OpenAI: "we had the model for ChatGPT in the API for ~10 months before we made ChatGPT .. I sort of thought someone (else) was gonna just build it" (reminder: there are many similarly unbuilt products right now)

near

642,147 次观看 • 3 年前