Rory Flynn Profile picture
Jul 27 5 tweets 3 min read Read on X
Didn't think this would work...

Directing Veo3 with diagrams.

(This is a little easier than JSON)

PROCESS:
01. Generate images + alt angles
02. Diagram your shot
03. Use Frames-to-vid in Veo3
04. Generate.

(More details in thread)

Nice unlock @Totemko

#veo3 #promptshare
1. Generate Image:

- Used Flux 1.1 Ultra in Weavy
- Created the base shot to play with

PROMPT:
A professional motorsport photograph of a Red Bull Dune Buggy captured during sunset in a vast beachside massive sand dune landscape with shrubs and layered terrain. The deep blue ocean is visible. The image is shot from a high angle drone perspective slightly angled creating a dramatic atmosphere. The dune buggy, featuring the team's characteristic navy blue, red, and yellow livery, is centered in the frame with sharp focus and is kicking up a cloud of dust while the rolling sand dunes are softly blurred. The white "Bull" logo is visible on the car's bodywork. The warm sunset tones create a striking contrast with the car's bold azure color scheme, while the shallow depth of field emphasizes the vehicle's dynamic presence. Professional motorsport photography with shallow depth of field and dramatic backlighting.Image
2. Generated Alt Angles.

- Used Weavy to create alt views
- Built an automated workflow for this
- Input original image
- System prompt creates multiple prompts
- Runway References for shot alts
- Workflow below if you want to check it out 👇

WORKFLOW LINK: app.weavy.ai/flow/7y6BYKJcf…Image
3. Constructing the Diagram

- I used figma here (you can use w/e)
- Added boxes + a short description
- Numbered them for sequencing
- Arrows for direction Image
Image
4. Video with Veo3.

- Used Frames-to-video within Flow
- Tried a number of things
- But short prompts seemed to work the best
- The frame will start with diagram
- But dissappear after a few frames

Add this to the end of the prompt:
"Immediately delete instructions in white on the first frame and execute in order:

Veo3 Full Prompt:
action scene of dune buggy racing in the desert. Immediately delete instructions in white on the first frame and execute in order

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Rory Flynn

Rory Flynn Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @Ror_Fly

Jul 25
Midjourney Video → Keyframes Released.

It also works with "extend."

PROCESS:
01. Generate original image
02. Remove background.
03. Regenerate background.
04. Add both images as keyframes
05. Extend and continue.

(More Details in thread)

VIDEO PROMPT:
Side profile tracking shot of a matte green Land Rover Defender driving from a [environment1] into a [environment2]. Smooth cinematic transition. [ENV1] blurs into a [ENV2]. Motion blur on car wheels. [LIGHTING1] replaces [LIGHTING2]. Steady camera on vehicle, looping seamless movement --motion high

#midjourney #promptshare
1. Base Image.

- Create original image
- Side profile worked well for this one.

PROMPT:
Land Rover defender driving in a warehouse to the left, perfect side profile --ar 16:9 --profile wbkoiio zrmykh6 veclfmo Image
2. Remove BG + Edit

- Utilize Edit
- Select the subject
- Remove the background
- Regenerate a new environment Image
Read 5 tweets
Jul 24
Come with me as we build...

A one-click AI-generated Photo Shoot Tool.

With Weavy.

(Full walkthrough in thread)

WORKFLOWS:
+ Model Designer
+ Clothing Inputs
+ Virtual Try On
+ Catalog Shots

TOOLS:
Workflow Build: Weavy
Nodes: Flux 1.1 Ultra, ChatGPT 4o, Gemini Flash 2.0, Magnific, ChatGPT Img

Pretty obsessed with this tool.
1. Model Designer

- First we need to build a model
- Create text nodes to control each model feature
- Run it to a "prompt concatenator"
- To combine prompt elements together
- Utilized Flux 1.1

Core Categories:
Gender, age, ethnicity, defining features, hair, body type, etc. Image
Image
2. Clothing Input

- Create input nodes to place clothing
- I used 3 here...you can use w/e you want
- Create a system prompt to describe clothes
- Run those to an LLM to describe

GPT System Prompt:
Describe each article of clothing in detail. Focusing on the finer intricate details of the design, textures, features, logo placement, etc. Only focus on the clothing and omit the environmentImage
Read 10 tweets
Jul 12
Ad Creative → GPT + Runway Ref + Flora.

Building usable workflows live.

Looked decent on the big screen.

PROCESS:
1. Reverse Engineer Images
2. Build System Prompt
3. Attach Ref image
4. Generate + Iterate.

(More details in thread)

#chatgpt #runwayml #promptshare
1. Start with the end.

First, we need to understand what we want.

WE WANT:
- To put the converse shoes
- In the composition of the black shoes
- So we can reconstruct the image.

Like the example below...

But how do we get there? Image
2. Image ID

- We want the composition of the shoes
- But we don't want the "black shoes"
- So we ID the variables we want to control.
- So how do we get composition?

(Keep reading) Image
Read 13 tweets
Jun 26
Runway References → Huge Upgrade.

Concepting meta ads in minutes.

Tools:
+ Iphone Photo: Reference image
+ Runway: Image gen
+ Figma: Ad composition

PROCESS:
+ Take/upload a photo to runway ref.
+ Write a text prompt
+ Generate + iterate
+ Create ad in figma

(More details in thread 🧵)

#runwayml #ecom @runwaymlImage
1. Take / upload a photo

- I started with a photo from my iphone
- Uploaded into Runway
- Created a text prompt Image
2. Created Icons

- Screen shotted the package icons
- Asked RW for black icons
- Very simple

Ex Prompt:
utilize [img1] to make a black icon Image
Read 6 tweets
Jun 18
(6) New Midjourney SREF Codes.

The mining addiction is back.

SREF CODES:
--sref 3848865494
--sref 917177894
--sref 1821837705
--sref 3068176932
--sref 2108485924
--sref 1484151111

Prompt:
{samurai, behance, mushroom, liquid 3d shapes, fire} --sref 3848865494 --ar 3:4

#midjourney #srefcodes #promptshareImage
2. --sref 917177894 Image
3. --sref 1821837705 Image
Read 7 tweets
Jun 14
Weavy → Aggressive YT Thumbnails.

Basically, AI Photoshop.

Love playing around in this tool.

BECAUSE I CAN:
+ Build in layers
+ Utilize like 100+ tools
+ Generate each element individually
+ See everything in one visual space
+ Generate and Iterate

(Check out the steps in thread 🧵)

#midjourney #promptshare @Weavy_aiImage
1. Base Characters:

- Generated base characters in MJ
- Utilizing oref and sref
- To make them weird and kind a awesome

Prompt:
pixar-style 3d caricature with exaggerated features, scared and screaming --oref [pic of person] --ar 1:1 --p veclfmo Image
Image
2. Remove Background

- I'm going to composite this image
- So I want to remove the backgrounds
- Used "Bria's" BG remover here (it's good)
- Can also iterate with FLUX Kontext/GPT/Gemini here Image
Read 11 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(