Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

When creating ingredient images, try to create stylistically consistent images. If you use input images that are too disparate, the output may lead to a cut scene. For example, when generating a reference image, try using a prompt like: “Create the next scene in this storyboard, now show a... show more

Google AI

2,306,818 subscribers

23,526 views • 9 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Here's a movie trailer from ChatGPT Images 2.0. Create a storyboard style image with Images 2.0, and use it in Seedream 2.0 as a reference. Enter a prompt to create a 15 second video from the image. The model will use the character and environments. Quick tutorial:

Here's a movie trailer from ChatGPT Images 2.0. Create a storyboard style image with Images 2.0, and use it in Seedream 2.0 as a reference. Enter a prompt to create a 15 second video from the image. The model will use the character and environments. Quick tutorial:

Jerrod Lew

15,768 views • 3 months ago

Create animated fight scenes with ChatGPT Images 2.0. Ask Images 2.0 to choreograph a scene and place it into a storyboard. Then use that image as a reference in Seedance 2.0 to bring it to life. It follows the storyboard sheet really well. Some examples:

Create animated fight scenes with ChatGPT Images 2.0. Ask Images 2.0 to choreograph a scene and place it into a storyboard. Then use that image as a reference in Seedance 2.0 to bring it to life. It follows the storyboard sheet really well. Some examples:

Jerrod Lew

12,501 views • 3 months ago

Create dialogue and action scenes with ChatGPT Images 2.0! Set up a storyboard, including characters, dialogue and the scene. Then bring the image to use as a reference for Seedance 2.0! You can have so much more control over your scene like this.

Create dialogue and action scenes with ChatGPT Images 2.0! Set up a storyboard, including characters, dialogue and the scene. Then bring the image to use as a reference for Seedance 2.0! You can have so much more control over your scene like this.

Jerrod Lew

12,364 views • 3 months ago

Google Labs just dropped Whisk, a fun new AI image tool. You can remix your ideas into digital magic. You can prompt or input image to create unique images from subject, scene, and style. Quick example and how to try:

Google Labs just dropped Whisk, a fun new AI image tool. You can remix your ideas into digital magic. You can prompt or input image to create unique images from subject, scene, and style. Quick example and how to try:

Min Choi

117,648 views • 1 year ago

You can basically generate your own custom visual stories using Gemini with just a single prompt 'This is a fictional movie set in a fantasy world similar to The Lord of the Rings. Use this as a starting point and imagine the next sequence of scenes. Create a series of separate images, each depicting a distinct moment in the story, presented in a sequential order like a storyboard. Include quotes for each image to narrate the events happening within it. Ensure the flow between images is consistent and logical, with each one styled like a cinematic movie shot that advances the narrative. Maintain the same format and visual style across all images to keep them cohesive'

You can basically generate your own custom visual stories using Gemini with just a single prompt 'This is a fictional movie set in a fantasy world similar to The Lord of the Rings. Use this as a starting point and imagine the next sequence of scenes. Create a series of separate images, each depicting a distinct moment in the story, presented in a sequential order like a storyboard. Include quotes for each image to narrate the events happening within it. Ensure the flow between images is consistent and logical, with each one styled like a cinematic movie shot that advances the narrative. Maintain the same format and visual style across all images to keep them cohesive'

Cristian Peñas ░░░░░░░░

38,500 views • 1 year ago

One prompt. Multiple gaming scenes 🎮 The Nano Banana agent can generate several images at once, using a reference image to keep the same person consistent across scenes. This example spans different gaming eras, but the same approach works for any theme or style. Images and videos, all in one place. Agent + prompt 👇

One prompt. Multiple gaming scenes 🎮 The Nano Banana agent can generate several images at once, using a reference image to keep the same person consistent across scenes. This example spans different gaming eras, but the same approach works for any theme or style. Images and videos, all in one place. Agent + prompt 👇

GLIF

10,882 views • 6 months ago

Introducing Ideogram Character -- the first character consistency model that works with just one reference image. Now available to all users for free! Create consistent character images in any style, expression, scene, and lighting. Who wants video next? 🥺

Introducing Ideogram Character -- the first character consistency model that works with just one reference image. Now available to all users for free! Create consistent character images in any style, expression, scene, and lighting. Who wants video next? 🥺

Ideogram

1,712,901 views • 1 year ago

DALL-E 3 Double Exposure Images Using ChatGPT's Custom Instructions. 🔖 Bookmark and Repost! If you find this useful, please share it with others! You can now easily create double exposure images by using the syntax Color::subject1::subject2 You can either input this directly into DALL-E 3 before generating images or incorporate it into your custom instructions. This command will automatically use the fixed prompt to generate 4 different images, each with a unique seed value. Paste this under ChatGPT's Custom Instructions or DALL-3 before starting conversation. { DE": { "Instruction": "Using will only use generic prompt and update place holder varaibles and nothing else' Genric Prompt: "Construct a [Color] double exposure image where [Subject #1] is intricately superimposed within the confines of [Subject #2], all set against a stark white background.' Create 4 images with different seeds without modifying the generic prompt." You will first create two images. Within the same request, you will generate two more without asking for any input from the user. In general, you will always create 4 images. Your response should be something like this: 'Here are the first two images along with their seed details.' You must always provide the seed number details for that image after it's rendered. Then 'I'll generate the next two images.' And finally 'Here are the remaining two images along with their seed details.' You will always use wide aspect ratio and You must always provide the seed number. When command is activated display full instruction and also confirm that you will only use genric prompt and nothing else and update only varaiable", "CommandFormat": "color::subject1::subject2", "Response": { "Initial": "Creating images based on the provided subjects...", "AfterFirstSet": "Here are the first two images along with their prompt and seed details.", "AfterSecondSet": "Here are the remaining two images along with their prompt and seed details." }, "ActivationCommand": "/activate DE" } } Example: To activate type: /activate DE Notes Start giving prompt like this blue::mountain::wolf red::city skyline::dancer green::forest::lion If you found this post helpful, don't forget to hit the like and follow buttons, and share it with others who might find it useful.

DALL-E 3 Double Exposure Images Using ChatGPT's Custom Instructions. 🔖 Bookmark and Repost! If you find this useful, please share it with others! You can now easily create double exposure images by using the syntax Color::subject1::subject2 You can either input this directly into DALL-E 3 before generating images or incorporate it into your custom instructions. This command will automatically use the fixed prompt to generate 4 different images, each with a unique seed value. Paste this under ChatGPT's Custom Instructions or DALL-3 before starting conversation. { DE": { "Instruction": "Using will only use generic prompt and update place holder varaibles and nothing else' Genric Prompt: "Construct a [Color] double exposure image where [Subject #1] is intricately superimposed within the confines of [Subject #2], all set against a stark white background.' Create 4 images with different seeds without modifying the generic prompt." You will first create two images. Within the same request, you will generate two more without asking for any input from the user. In general, you will always create 4 images. Your response should be something like this: 'Here are the first two images along with their seed details.' You must always provide the seed number details for that image after it's rendered. Then 'I'll generate the next two images.' And finally 'Here are the remaining two images along with their seed details.' You will always use wide aspect ratio and You must always provide the seed number. When command is activated display full instruction and also confirm that you will only use genric prompt and nothing else and update only varaiable", "CommandFormat": "color::subject1::subject2", "Response": { "Initial": "Creating images based on the provided subjects...", "AfterFirstSet": "Here are the first two images along with their prompt and seed details.", "AfterSecondSet": "Here are the remaining two images along with their prompt and seed details." }, "ActivationCommand": "/activate DE" } } Example: To activate type: /activate DE Notes Start giving prompt like this blue::mountain::wolf red::city skyline::dancer green::forest::lion If you found this post helpful, don't forget to hit the like and follow buttons, and share it with others who might find it useful.

AshutoshShrivastava

34,305 views • 2 years ago

Create amazing action scenes with Seedance 2.0! First, create your character sheet with ChatGPT Images 2.0, then bring it to Seedance 2.0 as a reference image. Prompt your scene and what happens, referencing the character. More details + prompts below.

Create amazing action scenes with Seedance 2.0! First, create your character sheet with ChatGPT Images 2.0, then bring it to Seedance 2.0 as a reference image. Prompt your scene and what happens, referencing the character. More details + prompts below.

Jerrod Lew

15,877 views • 2 months ago

This is Flint Image 🔥 Still generating images one by one? Generate four images from a single prompt for 67% less than standard generation. Same quality. More options. One generation. The math speaks for itself. Try it now!

This is Flint Image 🔥 Still generating images one by one? Generate four images from a single prompt for 67% less than standard generation. Same quality. More options. One generation. The math speaks for itself. Try it now!

each::labs

154,386 views • 13 days ago

Consistent characters from any angle. You can now create consistent characters and objects from any angle using Multi-Image Ref in Elements. → Upload up to 10 reference images → Save them as an Element → Tag them in your prompt → Specify the angle you want → Generate

Consistent characters from any angle. You can now create consistent characters and objects from any angle using Multi-Image Ref in Elements. → Upload up to 10 reference images → Save them as an Element → Tag them in your prompt → Specify the angle you want → Generate

LTX.io

12,167 views • 5 months ago

As I promised yesterday, I'll briefly explain LoRA training and share a workflow I made so you can do it quickly. First, let me answer a very common question: 'Why train LoRAs when we have such advanced models?' Even though we have incredibly advanced models now (like NBP), we still can't always get them to do specific things we want. Simplest example: the spritesheet LoRA I made the other day. I generated 1000 images with Nano Banana and only 100 were what I wanted. The LoRA I trained using those 100 images gives me nearly 100% consistent results. Second point is cost and speed. With LoRA, we can cut costs by 4-5x. And while doing that, we're generating 4-5x faster. How many images do you need for a good LoRA? This depends on your LoRA's complexity. For example, when I training the spritesheet LoRA, even though I used 100 images, I didn't include buildings in the training data, so this LoRA doesn't work for buildings. So think about your LoRA's use cases and add examples for as many use cases as possible to improve quality. What are paired images and how to train LoRAs for image-editing? When training LoRAs for image editing on fal, we call each edit example paired images - one with _start suffix, one with _end suffix. For example, if you're training a background remove LoRA, the unedited original photo will be your '_start' image. The image with background removed will be the '_end' image. Simply put: images we want to edit or use as reference get _start, target images we want to achieve get '_end'. Important: save both images with the same name. Like image332_start.jpg and image332_end.jpg. This way the system knows which images pair together. What about training LoRAs for models with multiple image inputs? Same logic. We still use _start and _end suffixes, but with one difference. Since there are multiple input images, we can number them: _start, _start1, _start2. Example: start images, 1st image = Woman portrait (image35_start.jpg) 2nd image = Glasses photo (image35_start1.jpg) 3rd image = Hat photo (image35_start2.jpg) Output image = portrait of woman wearing glasses and hat (image35_end.jpg) Can we do more detailed captioning? Yes. Similarly, you can improve training quality by creating a txt file for each set with the caption inside. Example: create image35.txt and write: 'Recreate the image by putting the glasses from the second image and the hat from the third image on the woman in the first image.' What are Steps? How many should I use? What's Learning Rate? Steps determines how many times the model sees and processes your training data (your images). Each step, the model learns a bit more. But as steps increase, so does the risk of overfitting. So there's no real default. But for a simpler LoRA with 20 paired images, 1000 steps is ideal. Here's a metaphor for the Steps and Learning Rate relationship: Imagine you have a balloon. Our goal is to inflate it to the optimal size. Steps = How many times we blow into the balloon Learning rate = How hard we blow each time If we blow too softly, we need to blow many more times. If we blow too hard, we risk popping it quickly and can't reach optimal size. Of course training won't explode, but it won't work as intended because it wasn't trained optimally. Training's done, now what? Once training's complete, you'll have a safetensors file. Every model you train on fal has a LoRA inference endpoint. In that inference, add your safetensors file link to the LoRA url input, and you can use your LoRA. Thanks for the read! The workflow in the video: If I forgot anything, let me know in the replies.

As I promised yesterday, I'll briefly explain LoRA training and share a workflow I made so you can do it quickly. First, let me answer a very common question: 'Why train LoRAs when we have such advanced models?' Even though we have incredibly advanced models now (like NBP), we still can't always get them to do specific things we want. Simplest example: the spritesheet LoRA I made the other day. I generated 1000 images with Nano Banana and only 100 were what I wanted. The LoRA I trained using those 100 images gives me nearly 100% consistent results. Second point is cost and speed. With LoRA, we can cut costs by 4-5x. And while doing that, we're generating 4-5x faster. How many images do you need for a good LoRA? This depends on your LoRA's complexity. For example, when I training the spritesheet LoRA, even though I used 100 images, I didn't include buildings in the training data, so this LoRA doesn't work for buildings. So think about your LoRA's use cases and add examples for as many use cases as possible to improve quality. What are paired images and how to train LoRAs for image-editing? When training LoRAs for image editing on fal, we call each edit example paired images - one with _start suffix, one with _end suffix. For example, if you're training a background remove LoRA, the unedited original photo will be your '_start' image. The image with background removed will be the '_end' image. Simply put: images we want to edit or use as reference get _start, target images we want to achieve get '_end'. Important: save both images with the same name. Like image332_start.jpg and image332_end.jpg. This way the system knows which images pair together. What about training LoRAs for models with multiple image inputs? Same logic. We still use _start and _end suffixes, but with one difference. Since there are multiple input images, we can number them: _start, _start1, _start2. Example: start images, 1st image = Woman portrait (image35_start.jpg) 2nd image = Glasses photo (image35_start1.jpg) 3rd image = Hat photo (image35_start2.jpg) Output image = portrait of woman wearing glasses and hat (image35_end.jpg) Can we do more detailed captioning? Yes. Similarly, you can improve training quality by creating a txt file for each set with the caption inside. Example: create image35.txt and write: 'Recreate the image by putting the glasses from the second image and the hat from the third image on the woman in the first image.' What are Steps? How many should I use? What's Learning Rate? Steps determines how many times the model sees and processes your training data (your images). Each step, the model learns a bit more. But as steps increase, so does the risk of overfitting. So there's no real default. But for a simpler LoRA with 20 paired images, 1000 steps is ideal. Here's a metaphor for the Steps and Learning Rate relationship: Imagine you have a balloon. Our goal is to inflate it to the optimal size. Steps = How many times we blow into the balloon Learning rate = How hard we blow each time If we blow too softly, we need to blow many more times. If we blow too hard, we risk popping it quickly and can't reach optimal size. Of course training won't explode, but it won't work as intended because it wasn't trained optimally. Training's done, now what? Once training's complete, you'll have a safetensors file. Every model you train on fal has a LoRA inference endpoint. In that inference, add your safetensors file link to the LoRA url input, and you can use your LoRA. Thanks for the read! The workflow in the video: If I forgot anything, let me know in the replies.

ilker

15,133 views • 6 months ago

2. Use the generated image as an image prompt for Runway or any video model that supports End-Frames. Use the image as the final/last frame and create a prompt that reveals the image in an ink-style animation. Example prompt:

2. Use the generated image as an image prompt for Runway or any video model that supports End-Frames. Use the image as the final/last frame and create a prompt that reveals the image in an ink-style animation. Example prompt:

Halim Alrasihi

14,596 views • 1 year ago

Reve just launched and the early results are 🤯 🎨 Spatially intelligent generation, create multi-image layouts in one shot 🖌️ Reference images to craft the perfect scene 🎭️ State of the art image editing capabilities

Reve just launched and the early results are 🤯 🎨 Spatially intelligent generation, create multi-image layouts in one shot 🖌️ Reference images to craft the perfect scene 🎭️ State of the art image editing capabilities

fal

31,292 views • 9 months ago

Seedream 5.0 Pro is now in Runway. Generate highly detailed images from a prompt or reference, with legible in-image text in up to 14 different languages. Try it now at the link below.

Seedream 5.0 Pro is now in Runway. Generate highly detailed images from a prompt or reference, with legible in-image text in up to 14 different languages. Try it now at the link below.

Runway

21,048 views • 27 days ago

Introducing StyleDrop, a model that allows a significantly higher level of stylized text-to-image synthesis by using a few style reference images that describe the style for text-to-image generation, bypassing the burden of text prompt engineering. More→

Introducing StyleDrop, a model that allows a significantly higher level of stylized text-to-image synthesis by using a few style reference images that describe the style for text-to-image generation, bypassing the burden of text prompt engineering. More→

Google AI

80,378 views • 2 years ago

This GPT Image 2 prompt creates cinematic storyboard grids from your reference images while generating an original continuous sequence. You can see two different examples in the attached video. If you want a director-inspired cinematic tone, first use the separate “director language” prompt with a director name. It gives you abstract cinematic qualities without directly replicating copyrighted styles. If you don’t want that, you can simply remove that paragraph from the grid prompt. Then you can use the Seedance 2.0 prompt I shared to animate the storyboard grid into a cinematic sequence. You can find the prompts below.

This GPT Image 2 prompt creates cinematic storyboard grids from your reference images while generating an original continuous sequence. You can see two different examples in the attached video. If you want a director-inspired cinematic tone, first use the separate “director language” prompt with a director name. It gives you abstract cinematic qualities without directly replicating copyrighted styles. If you don’t want that, you can simply remove that paragraph from the grid prompt. Then you can use the Seedance 2.0 prompt I shared to animate the storyboard grid into a cinematic sequence. You can find the prompts below.

Kōda

10,914 views • 2 months ago

I created a 3D Gaussian Splat of my kitchen using 1/3rd the images it used to take me by using NVIDIA AI Developer's 3DGRUT! I can now use 180 degree fisheye images and ray tracing to make detailed splats. The only reason the scene isn't sharper is because my input images weren't super sharp - when I took the images back in October, I was still learning to use the lens. I plan to make a "first reactions/overview video". Tutorial after that. For reference, this took 206 images and the ultrawide on my iPhone took 608 images to capture. #3D #AEC #Computervision

I created a 3D Gaussian Splat of my kitchen using 1/3rd the images it used to take me by using NVIDIA AI Developer's 3DGRUT! I can now use 180 degree fisheye images and ray tracing to make detailed splats. The only reason the scene isn't sharper is because my input images weren't super sharp - when I took the images back in October, I was still learning to use the lens. I plan to make a "first reactions/overview video". Tutorial after that. For reference, this took 206 images and the ultrawide on my iPhone took 608 images to capture. #3D #AEC #Computervision

Jonathan Stephens

30,663 views • 1 year ago

🎬On Lovart, try Veo 3.1 Multi-Image mode. Upload your images + prompt to create cinematic magic. Post your video in the comments—show us what you’ve got!

🎬On Lovart, try Veo 3.1 Multi-Image mode. Upload your images + prompt to create cinematic magic. Post your video in the comments—show us what you’ve got!

LovartAI

17,476 views • 6 months ago

1/ Introducing Playground with Mixed Image Editing. A new way to combine real and synthetic images to create stunning works of art & photorealistic images bound only by your imagination. Try now:

1/ Introducing Playground with Mixed Image Editing. A new way to combine real and synthetic images to create stunning works of art & photorealistic images bound only by your imagination. Try now:

Suhail

599,475 views • 3 years ago