#40 - SPECIAL: GPT-X, Diffusion, and our Multimodal Future Part II

Sep 22, 2022

01:15:05

forum

Ask episode

view_agenda

Chapters

auto_awesome

Transcript

info_circle

Episode notes

What could an AI creative tool like DALL-E 2 or Midjourney look like in the next few years?

This video explores the full set of future possibilities upon us!

GPT-X, Diffusion, and our Multimodal Future (Part II) BOOK: https://docs.google.com/document/d/1TeRMqOsGX8kiK_mNiCt4yxO26Yjk6BdM/

Timestamps:

00:00 - Intro
05:02 - Multimodal Model Characteristics
11:26 - Creating a new image
15:56 - Prompt writing capabilities - Prompt Formatting
16:50 - Prompt autocompletion, intelligent suggestions
19:57 - Built in prompt unbundling
21:57 - Configure Recombinants
23:45 - Recombinant blending modes
25:07 - Configure Recombinant Unbundling Details
26:12 - Recombinant Layers & Node based
28:05 - Recombinant Import Bench
29:48 - Natural Language Image editing - refresh individual objects
31:44 - Edit mode - Natural Langauge Edit Prompts
32:37 - Edit prompt realtime feedback
33:05 - Natural language hex color editing support
34:35 - Advanced Natural Language Edit Prompt Changes
35:53 - Edit prompt intensity (UI controls)
36:59 - Multimodal Object Transformations
37:16 - Lighting & Camera Controls
38:00 - Advanced Editing Tools (Fix AI Weirdness and more)
39:27 - Edit images via markup (markup prompt)
40:43 - Logical Variations
43:57 - Realtime Collaboration
44:28 - Recombinant Collaborators
46:06 - Built in Music Player
48:45 - Creative Hyperparameters
49:20 - Text Capabilities - Magic Text
50:52 - Text Capabilities - Magic Text Fill
52:41 - Latent Variation Scrubbing
53:34 - Explore Alternatives
56:34 - Productivity and commercialization
58:06 - Analysis & Feedback
59:16 - Advanced Multimodal Capabilities
1:03:45 - Offline Capabilities
1:11:11 - Advanced Workflow Support
1:11:58 - Closing thoughts