Make prompts people will pay you for with aitextpromptgenerator.com
This Prompt = “a full body portrait of a knight made from soggy scales, by Lukas Esch,by Filip Hodas,realistic,cgi” — Midjourney
Start here:
1
Editors Choice Quick Start Settings Cheat Sheet — (Beginners Settings) (In Step 3.Settings) Steps — 300 “clip_guidance_scale”: 5000, “tv_scale”: 0, “range_scale”: 150, “sat_scale”: 0, “cutn_batches”: 2, (In Step 4.diffuse) n_batches: 1 Leave all other default values alone Try this text prompt for fun = “An adorable portrait of a cute puppy, trending on artstation” Or generate your own text prompts here https://aitextpromptgenerator.com
Let’s get the right settings first
Navigate to colab.research.google.com/github/alembics/disco…
In colab the first window you opened — Scroll down to (3.Settings) To set your batch name. Your batch name is what you want these image/images set to be named.
4
Set the steps between 250 to 1000, The higher the number the more cycles the ai will use to produce the image (INFO) Increasing steps will provide more opportunities for the AI to adjust the image, and each adjustment will be smaller, and thus will yield a more precise, detailed image. Increasing steps comes at the expense of longer render times. Also, while increasing steps should generally increase image quality, there is a diminishing return on additional steps beyond 250–500 steps. However, some intricate images can take 1000, 2000, or more steps. It is really up to the user. Just know that the render time is directly related to the number of steps, and many other parameters have a major impact on image quality, without costing additional time.
5
Set Clip Guidance scale between 150–60,000 — Editors Choice — 30,000 (INFO) clip_guidance_scale: (150–60,000) CGS is one of the most important parameters you will use. It tells DD how strongly you want CLIP to move toward your prompt at each timestep. Higher is generally better, but if CGS is too strong it will overshoot the goal and distort the image. So a happy medium is needed, and it takes experience to learn how to adjust CGS.
6
Click “tv_scale:” Set between 0–1,000 Editors choice — 200 (INFO) Total variance denoising. Optional, set to zero to turn off. Controls ‘smoothness’ of final output. If used, tv_scale will try to smooth out your final image to reduce overall noise. If your image is too ‘crunchy’, increase tv_scale. TV denoising is good at preserving edges while smoothing away noise in flat regions. See en.wikipedia.org/wiki/Total_variation_denoising
7
Set range_scale between 150–1000 Editors Choice — 180 (INFO) Optional, set to zero to turn off. Used for adjustment of color contrast. Lower range_scale will increase contrast. Very low numbers create a reduced color palette, resulting in more vibrant or poster-like images. Higher range_scale will reduce contrast, for more muted images.
8
Set Cutn_batches between 2–8 choosing an even number Editors Choice — 6 (INFO) cutn_batches: (2–8) Each iteration, the AI cuts the image into smaller pieces known as cuts, and compares each cut to the prompt to decide how to guide the next diffusion step. More cuts can generally lead to better images, since DD has more chances to fine-tune the image precision in each timestep.
9
Inside the (3.Settings) Open the extra settings tab
10
Set eta between 0.1- 1 Editors Choice — 0.8 (INFO) eta: is a diffusion model variable that mixes in a random amount of scaled noise into each timestep. 0 is no noise, 1.0 is more noise. As with most DD parameters, you can go below zero for eta, but it may give you unpredictable results.
11
Set cut_ic_pow between 2–8 Editors Choice — 2 (INFO) cut_ic_pow: (1.0|0.5–100) This sets the size of the border used for inner cuts. High cut_ic_pow values have larger borders, and therefore the cuts themselves will be smaller and provide finer details. If you have too many or too-small inner cuts, you may lose overall image coherency and/or it may cause an undesirable ‘mosaic’ effect. Low cut_ic_pow values will allow the inner cuts to be larger, helping image coherency while still helping with some details.
12
OPTIONAL: Select horizontal or vertical symmetry between 0.5–35
13
Inside (4. Diffuse!) Click the n_batches and set number of different images you want to make. 1 to 5 is recommended. You can do more but time outs and other errors may occur.
14
Check the skip_video_for_run_all . This turns off the video rendering to speed up image processing. Leave unchecked if you want it to render a video as well. (USES MORE RESOURCES)
Now we can set the image prompt
15
Back up to Inside (3.Settings) under Prompts paste in your what you want your image to look like. Use this generator to help you make awesome images right away https://aitextpromptgenerator.com IMPORTANT — Paste your text prompt in between the quotes, example below 0: [“ Paste Your prompt text here inside the quotes “], Do not modify any of the code outside of the quotes (INFO) text_prompts: Phrase, sentence, or string of words and phrases describing what the image should look like. The words will be analyzed by the AI and will guide the diffusion process toward the image(s) you describe. These can include commas and weights to adjust the relative importance of each element. E.g. “A beautiful painting of a singular lighthouse, shining its light across a tumultuous sea of blood by greg rutkowski and thomas kinkade, Trending on artstation.” Notice that the default prompt loosely follows a structure: [subject], [details], [setting], [meta modifiers and artist]; this is a good starting point for your experiments.
16
Click the runtime tab at the top menu bar
17
Select Run all option.
18
Click “Connect to Google Drive”
19
Select your google account
20
Click “Allow”
21
Your should now see the code start to run, and your image should appear near the bottom of the page as it begins to generate. Final copy will be saved to your google drive. (INFO) Getting your output Disco Diffusion will store your your images and videos into your google drive in: \My Drive\AI\Disco_Diffusion\images_out\batch_name. You can browse to this directory in a second window to monitor progress, and download the entire folder when your project is complete.
This article was sponsored by aitextpromptgenerator.com
MAKE BETTER PROMPTS FAST :An innovative platform that allows you to generate custom prompts that can be used with any AI art generator, such as Midjourney, Stable Diffusion, Disco Diffusion, DALL-E, and more.
The platform’s prompt builder makes it easy to create custom prompts that are specific to your project or desired outcome. With just a few clicks, you can generate high-quality images that are perfect for use in various industries, including art, design, marketing, and more. The Stable Diffusion AI Art Generator, which is used by aitextpromptgenerator.com, is renowned for delivering superior image results, making it a popular choice for image generation.
What sets aitextpromptgenerator.com apart from other AI-based image generators is its focus on customization and control. The prompt builder feature allows you to create prompts from scratch, giving you more control over the images you generate. You can tailor the prompts to your specific needs, resulting in images that are unique to your project.
In summary, aitextpromptgenerator.com is a fantastic platform for generating custom prompts that can be used with any AI art generator. It offers a simple and effective way to generate high-quality images that are tailored to your needs, all while giving you more control over the process. Whether you’re an artist, designer, marketer, or anyone in need of high-quality images, aitextpromptgenerator.com is the perfect tool to help you unleash your creativity and achieve your goals with ease.
