Talking Faces with AI | Deep Dive Live Project [DDLP]
The First DDLP - Deep Dive Live Project!
This is where i have an idea and run it from start to finish, demonstrating a fully applied concept to completion. Along the way i can suggest branching choices which can be taken to further enhance the final version. This will use multiple services & methods with many AI services & software on display. In the end we can see what we must pay attention to while exposing some routes to improve this concept.
discord: / discord
www.fivebelowfive.uk
Links:
https://claude.ai/Civitai
https://civitai.com/
https://www.audacityteam.org/
https://www.kits.ai/
https://www.hedra.com/
https://adobe.com
https://lumalabs.ai/dream-machine
Sections:
00:00:00 Demo Video
00:00:30 Introduction to DDLP
00:05:30 Script Concept (CLAUDE)
00:14:08 Image Dataset (LORA)
00:17:52 Lora Training (CIVITAI)
00:21:28 Initial Image Gens (COMFYUI)
00:34:10 Puppet Options discussion
00:59:59 Speech Dataset (AUDACITY)
01:01:56 Phoneme Speech method
01:09:17 Speech Model Training (KITSAI)
01:15:22 Audacity, silence injection/removal
01:17:50 Lipsync Video gen (HEDRA)
01:24:31 Rotoscoping (AFTER EFFECTS)
01:31:09 Dream Machine BG scenes (LUMAAI)
01:42:05 First Draft
01:52:06 Results & Conclusions
Workflow Packs:
Hyper SUPIR https://civitai.com/models/444002
Merge Models https://civitai.com/models/432863
cosXL Convertor https://civitai.com/models/420384
Looped Motion https://civitai.com/models/410919
Trio Triple Latents https://civitai.com/models/381021
Ananke Hi-Red https://civitai.com/models/352117/ana...
SDXL Lora's
https://civitai.com/models/384333/hel...
https://civitai.com/models/401458/not...
https://civitai.com/models/405640/pau...
https://civitai.com/models/339881/ass...
https://civitai.com/models/320332/ass...
https://civitai.com/models/308724/zen...
https://civitai.com/models/125217/spa...
https://civitai.com/models/117624/asc...
https://civitai.com/models/117546/wom...
https://civitai.com/models/106864/sdx...
Introducing series (music/video)
Noisee.ai • Introducing Noisee.ai AMV Generator [Video]
Udio.com • Introducing Udio.com [music]
suno.com • Introducing Suno V3 Music
haiper.ai • Introducing Video Generation with Haiper AI
Checkpoint Merging
• Create The Best Model Mixes with DJZ Merge...
cosXL / cosXL-edit conversion
• Convert any SDXL model to cosXL-edit
• Unlock CosXL with any SDXL Checkpoint [cos...
3D Generation
• DJZ 3D Collection
New Diffusion Models (April '24)
Stable Cascade:
• Stable Cascade Comfy Checkpoint Update
• Stable Cascade in ComfyUI - Fully Supported!
SDXS-512:
• SDXS - New Image Generation model
cosXL & cosXL-edit:
• CosXL & CosXL-Edit - New Instruct Pix2Pix ...
Stable Cascade series:
• Stable Cascade Workflows [March 2024]
Image Model Training
datasets • Datasets in detail - Model Training #comfyui
colab • Updated Lora Training Notebook #colab (free)
local • Updated Lora Training Notebook #colab (free)
civitai • Stable Cascade LORA training
civitai • SDXL Lora Training with CivitAI, walkthrough
Music with Audacity
• Make Music with Audacity AI - Mashup Resty...
• Make Music with Audacity AI [Music]
DJZ custom nodes (aspectsize node)
• AspectSize (djz-nodes) #ComfyUI
stable diffusion cascade
stable diffusion lora training
comfyui nodes explained
comfyui video generation
comfyui tutorial 2024
best comfyui workflows
comfyui image to image
comfyui checkpoints
civitai stable diffusion tutorial