filmov
tv
FLUX and DiffusionBee 2.5.3
Показать описание
In today's video, I dive into the latest update to DiffusionBee 2.5.3, a fast and innovative stable diffusion application.
this released update to DiffusionBee lets you Utilize Flux and embeddings
With everything ran locally on your computer offline
O:10 intro
1:04 terminology
1:14 what is StableDiffusion?
1:23 what is prompting?
1:40 What are embedding?
2:51 what are image weights?
3:03 what are safetenors?
3:29 what are LoRa?
4:00 what are Flux Models?
4:13 what are Pony models?
4:47 what is safe for work mode?
4:49 XL LoRa and XL base models?
5:08 What is negative prompting?
5:20 What are samplers?
6:35 What are step counts?
7:22 What are Flux models and step counts?
8:25 Computer specs, and benchmarks
9:40 what’s missing? ?
10:10 downloading App
12:35 New Layout
14:11 importing models
15:42 embedding installation
17:13 importing LoRa
18:06 compatible models on civitai
18:33 navigating the home screen
18:57 text2img
27:27 weighting
34:37 Styles drop-down menu
36:10 Flux and style demo
40:56 Controlnet
40:58 Depth map
43:05 Bodypose
43:56 Lineart
45:08 Scribble
47:00 Tile / img2img technique
51:40 LoRa
53:48 Trigger words
57:17 img2img
1:04:00 Ai Canvas
1:12:36 Illustration Generator
1:19:05 Inpainting
1:24:32 upscaler
1:27:18 upscayl upscaling alternative tool
1:29:10 history tab breakdown
1:31:06 FLUX Schnell vs Dev
1:50:54 Training
1:51:56 resizing images
1:53:05 captioning
THE APP
WEBSITE
My models
Resize Images
Clean up photos if you don’t have photoshop:
AI model training service:
Tool to convert txt to Json:
Captioning tools:
QR Code maker
Materials:
the needed python script, read me file [with all the instructions as seen in the video] as well as my batch text document installer from my previous video for captioning tutorial
Original GitHub source for code
[to:when] - adds to to the prompt after a fixed number of steps (when)
[from::when] - removes from from the prompt after a fixed number of steps (when)
Example: a [fantasy:cyberpunk:16] landscape..
At start, the model will be drawing a fantasy landscape.
After step 16, it will switch to drawing a “cyberpunk landscape”, continuing from where it stopped with fantasy.
Article---
[object:X] - adds object after a X steps
[object::X] - removes object after a X steps
[object1:object2:0.X] - first X% is object1, then swaps to object2
[object1:object2:X] - starts with object1, then changes to object2 at step X
[object1|object2] - alternates between object1 and object2 every step
[object1|object2|...|objectN] - alternates between object1 ... objectN, then loops back to object1
MORE articles to read:
cheatsheet:
a (word) - increase attention to word by a factor of 1.1
a ((word)) - increase attention to word by a factor of 1.21 (= 1.1 * 1.1)
a [word] - decrease attention to word by a factor of 1.1
a (word:1.5) - increase attention to word by a factor of 1.5
a (word:0.25) - decrease attention to word by a factor of 4 (= 1 / 0.25)
a \(word\) - use literal ( ) characters in prompt
[word | word] - a different way to blend multiple prompts, weights can be used
(word | word) - a different way to blend multiple prompts, weights can be used
word AND word - a different way to blend multiple prompts, weights can be used
[word:to:word] - [lion:robot] (This blends lion and robot equally)
[word:word:step] - lion:robot:20
(This means that 20 steps in, and it will change to the robot prompt.
#theprotoart #diffusionbee #diffusionbetutorial #howtousediffusionbee #howto #stablediffusionXL #stablediffusion #stablediffusiontutorial #art #artist #fluxschnell #DigitalArt #illusiondiffusion #ArtTips #ArtTutorials #fluxdev #DiffusionArt #DigitalArt #ArtTutorials #DigitalIllustration #img2img #flux
this released update to DiffusionBee lets you Utilize Flux and embeddings
With everything ran locally on your computer offline
O:10 intro
1:04 terminology
1:14 what is StableDiffusion?
1:23 what is prompting?
1:40 What are embedding?
2:51 what are image weights?
3:03 what are safetenors?
3:29 what are LoRa?
4:00 what are Flux Models?
4:13 what are Pony models?
4:47 what is safe for work mode?
4:49 XL LoRa and XL base models?
5:08 What is negative prompting?
5:20 What are samplers?
6:35 What are step counts?
7:22 What are Flux models and step counts?
8:25 Computer specs, and benchmarks
9:40 what’s missing? ?
10:10 downloading App
12:35 New Layout
14:11 importing models
15:42 embedding installation
17:13 importing LoRa
18:06 compatible models on civitai
18:33 navigating the home screen
18:57 text2img
27:27 weighting
34:37 Styles drop-down menu
36:10 Flux and style demo
40:56 Controlnet
40:58 Depth map
43:05 Bodypose
43:56 Lineart
45:08 Scribble
47:00 Tile / img2img technique
51:40 LoRa
53:48 Trigger words
57:17 img2img
1:04:00 Ai Canvas
1:12:36 Illustration Generator
1:19:05 Inpainting
1:24:32 upscaler
1:27:18 upscayl upscaling alternative tool
1:29:10 history tab breakdown
1:31:06 FLUX Schnell vs Dev
1:50:54 Training
1:51:56 resizing images
1:53:05 captioning
THE APP
WEBSITE
My models
Resize Images
Clean up photos if you don’t have photoshop:
AI model training service:
Tool to convert txt to Json:
Captioning tools:
QR Code maker
Materials:
the needed python script, read me file [with all the instructions as seen in the video] as well as my batch text document installer from my previous video for captioning tutorial
Original GitHub source for code
[to:when] - adds to to the prompt after a fixed number of steps (when)
[from::when] - removes from from the prompt after a fixed number of steps (when)
Example: a [fantasy:cyberpunk:16] landscape..
At start, the model will be drawing a fantasy landscape.
After step 16, it will switch to drawing a “cyberpunk landscape”, continuing from where it stopped with fantasy.
Article---
[object:X] - adds object after a X steps
[object::X] - removes object after a X steps
[object1:object2:0.X] - first X% is object1, then swaps to object2
[object1:object2:X] - starts with object1, then changes to object2 at step X
[object1|object2] - alternates between object1 and object2 every step
[object1|object2|...|objectN] - alternates between object1 ... objectN, then loops back to object1
MORE articles to read:
cheatsheet:
a (word) - increase attention to word by a factor of 1.1
a ((word)) - increase attention to word by a factor of 1.21 (= 1.1 * 1.1)
a [word] - decrease attention to word by a factor of 1.1
a (word:1.5) - increase attention to word by a factor of 1.5
a (word:0.25) - decrease attention to word by a factor of 4 (= 1 / 0.25)
a \(word\) - use literal ( ) characters in prompt
[word | word] - a different way to blend multiple prompts, weights can be used
(word | word) - a different way to blend multiple prompts, weights can be used
word AND word - a different way to blend multiple prompts, weights can be used
[word:to:word] - [lion:robot] (This blends lion and robot equally)
[word:word:step] - lion:robot:20
(This means that 20 steps in, and it will change to the robot prompt.
#theprotoart #diffusionbee #diffusionbetutorial #howtousediffusionbee #howto #stablediffusionXL #stablediffusion #stablediffusiontutorial #art #artist #fluxschnell #DigitalArt #illusiondiffusion #ArtTips #ArtTutorials #fluxdev #DiffusionArt #DigitalArt #ArtTutorials #DigitalIllustration #img2img #flux
Комментарии