demobook

AI Image Generator

412 clips across 102 tools — filter and play.

412 clips
  1. 2:210:30High-quality generation with Firefly Image Model 4 UltraThe user demonstrates switching to the premium Firefly Image Model 4 Ultra to generate a higher-quality, single-image result from the same prompt and reference.Adobe Firefly · beginner
  2. 2:510:16Using Prompt Enhancement in Adobe FireflyThe video shows the 'prompt enhancement' feature which automatically expands a simple prompt into a more detailed description to improve the AI output.Adobe Firefly · beginner
  3. 3:570:37Organizing and editing in Firefly BoardsThe demonstration shows how to use Firefly Boards to arrange multiple generated images side-by-side, remove backgrounds, and use artboards as style references.Adobe Firefly · beginner
  4. 10:170:20Comparing DDPM sampling with and without noise in Stable Diffusion 2The demo shows the difference in output quality when generating a 'tree in the desert' using Stable Diffusion 2, contrasting a sharp image with a blurry one when the noise step is removed.Stable Diffusion · Stable Diffusion · intermediate
  5. 33:080:29Adjusting Classifier-Free Guidance scale in Stable DiffusionThe demonstration shows how increasing the guidance scale alpha from 0 to higher values causes a tree to physically grow and gain detail within a desert scene in Stable Diffusion.Stable Diffusion · Stable Diffusion · intermediate
  6. 4:580:06Design characters with MidjourneyThe video shows the iterative process of using Midjourney to design the visual appearance of the 'Optimax 5000' robot character.Midjourney · intermediate
  7. 2:280:13Add text to images with Gemini 2.5 FlashThe demonstration shows the model's ability to render text for ads and memes, while also highlighting its failure to spell words correctly by adding extra characters.Gemini · Nano Banana · beginner
  8. 8:418:40Building a ComfyUI workflow from scratchA step-by-step walkthrough of adding nodes (Checkpoint, CLIP Text Encode, KSampler, VAE Decode) and connecting them to build a custom image generation pipeline.ComfyUI · advanced
  9. 19:571:09Generating a medieval warrior with batch processingDemonstrates generating multiple images of a medieval warrior by increasing the batch size in the Empty Latent Image node.ComfyUI · Stable Diffusion · advanced
  10. 25:330:32Importing workflows from image metadataShows how to drag an existing AI-generated image into the ComfyUI canvas to automatically reconstruct the entire node workflow used to create it.ComfyUI · advanced
  11. 58:094:05Controlling character poses with ControlNetDemonstrates using the OpenPose pre-processor and ControlNet Union model to force a generated princess character into a specific pose from a reference image.ComfyUI · Flux · advanced
  12. 5:052:09Generate scene images with multiple characters in OpenArtThe video shows how to use the OpenArt workflow to place two previously created characters into a single generated scene image using specific character prompts.OpenArt · intermediate
  13. 1:360:57Install custom workflows and missing nodes in ComfyUIThe video demonstrates how to drag and drop a JSON workflow file into ComfyUI and use the Manager to identify and install missing custom nodes.ComfyUI · advanced
  14. 3:020:20Search and install models via Model ManagerA walkthrough of using the ComfyUI Model Manager to search for specific AI models, such as ControlNet, and install them directly.ComfyUI · advanced
  15. 3:281:10Running and managing image generation queuesDemonstration of starting a workflow using the 'Run' button, setting up 'Run Instant' for continuous generation, and using 'Run on Change' to trigger generation upon prompt edits.ComfyUI · advanced
  16. 4:590:55Navigating the ComfyUI workspace and UI settingsShows how to use zoom, fit view, pan modes, and toggle link visibility or themes (light/dark mode) within the ComfyUI interface.ComfyUI · advanced
  17. 11:311:49Adding and connecting nodes in ComfyUIThe video demonstrates adding a 'Load Image' node via the library or right-click menu and connecting it to other nodes like 'Save Image' using spaghetti links.ComfyUI · advanced
  18. 19:431:34Converting widgets to inputs in ComfyUIShows how to convert a node's internal settings (like seed) into an external input pin and connect a 'Primitive' node to control it.ComfyUI · advanced
  19. 25:032:06Managing seeds and randomizationShows the difference between 'Randomize' and 'Fixed' seed settings in the KSampler to either generate new variations or reproduce the same image.ComfyUI · advanced
  20. 36:450:34Saving images to specific foldersShows how to use the 'Save Image' node and file path syntax to organize output images into custom subfolders.ComfyUI · advanced
  21. 0:490:37Launch Fooocus on Google ColabThe user demonstrates how to connect and run the Fooocus AI tool using a Google Colab notebook to prepare the environment for image generation.Fooocus · Stable Diffusion · intermediate
  22. 9:173:04Install ComfyUI using Easy InstallThe instructor demonstrates how to download the ComfyUI Easy Install zip from GitHub, extract it, and run the BAT file to set up a portable local installation.ComfyUI · advanced
  23. 13:355:23ComfyUI Interface OverviewA walkthrough of the ComfyUI UI, demonstrating the canvas, node search, top bar controls, view settings, and how to properly close the application.ComfyUI · advanced
  24. 18:588:14Running a Ready-Made WorkflowThe video shows how to load a .json workflow, download the required Juggernaut Reborn model, refresh the node list, and generate an image of a cat.ComfyUI · Stable Diffusion · advanced
  25. 44:186:05Using Math and Grouping NodesThe instructor shows how to use Math Int and Preview as Text nodes for automation and how to organize nodes into Groups for better workflow management.ComfyUI · advanced
  26. 1:12:0414:42Building a Text-to-Image Workflow from ScratchA step-by-step build of a standard diffusion pipeline using Load Checkpoint, CLIP Text Encode, Empty Latent Image, KSampler, and VAE Decode.ComfyUI · Stable Diffusion · advanced
  27. 1:48:162:58Managing Custom Nodes with ComfyUI ManagerThe video walks through searching for, installing, and uninstalling custom nodes (specifically the 'Align' node) using the built-in Manager.ComfyUI · advanced
  28. 2:47:359:01Guiding Structure with ControlNetThe video shows how to use Canny and Depth ControlNet models with pre-processors to guide image generation based on an input sketch or 3D text.ComfyUI · Stable Diffusion · advanced
  29. 3:11:488:27Generating Images with Z-Image TurboA demonstration of setting up the modern Z-Image Turbo model, including the specific Model Sampling AuraFlow node and high-quality prompt generation.ComfyUI · advanced
  30. 4:13:595:52Integrating ChatGPT API for Prompt GenerationThe instructor demonstrates signing into the ComfyUI API and using a ChatGPT node to automatically generate detailed image prompts for local models.ComfyUI · advanced
  31. 4:300:28Image remixing and text generation in IdeogramThe demo shows Ideogram generating legible text within images and using its 'remix' and 'upscale' tools to modify existing visuals.Ideogram · intermediate · Graphic Design & Vector Art
  32. 0:080:26Build modular AI scenes with Hedra ElementsThe video demonstrates using Hedra Elements to select and stack pre-generated assets like characters, outfits, and environments to create visual variations. It also shows how to upload custom faces or products to integrate them into the generation system.HHedra
  33. 2:051:21Character design and iteration with InVideo Agent 1The user directs the AI to generate gladiator character storyboards, iteratively refining the visual style using reference images and natural language commands to remove sci-fi elements.InVideo · beginner · Social Media & Content Creation
  34. 3:410:20Environment generation and prompt engineeringInVideo Agent 1 generates detailed environment concepts and automatically crafts complex prompts based on the established project context.InVideo · beginner · Social Media & Content Creation
  35. 3:150:18Generate AI images with MidjourneyThe user demonstrates the image generation workflow in GlobalGPT by using a cyberpunk prompt with the Midjourney model.GlobalGPT · beginner
  36. 2:251:20Midjourney Web Interface and OrganizationThe video demonstrates how to generate images using the 'Imagine' prompt bar on the Midjourney website and how to organize generations into smart folders using keywords.Midjourney · intermediate
  37. 7:261:32Using the Stylize ParameterA demonstration of how the --stylize (or --s) parameter affects artistic output, comparing low values for realistic 'child drawings' versus high values for complex aesthetics.Midjourney · intermediate
  38. 8:581:51Exploring Weirdness and Chaos ParametersThe video shows how the --weird parameter introduces unconventional aesthetics and how the chaos parameter creates diverse initial image grids.Midjourney · intermediate
  39. 14:320:17Negative Prompting with the No ParameterThe user demonstrates removing specific objects (like bananas) from a generated fruit bowl using the --no parameter.Midjourney · intermediate
  40. 14:490:57Using Seed Numbers for ConsistencyThe demo shows how to copy a seed number from a previous generation and reuse it to maintain composition across different prompts.Midjourney · intermediate
  41. 47:341:24Training Midjourney PersonalizationShows the process of ranking image pairs in the 'Tasks' tab to generate a unique personalization code (--p) for custom aesthetics.Midjourney · intermediate
  42. 24:211:50Setting up Z-Image Turbo in ComfyUIA walkthrough of loading the Z-Image Turbo JSON workflow into ComfyUI, updating the manager, and selecting the required text encoder and VAE models.ComfyUI · advanced
  43. 26:113:39Local image generation using Z-Image TurboThe video shows the process of generating an image locally in ComfyUI, explaining parameters like shift value, step count, and CFG for the Z-Image model.ComfyUI · advanced
  44. 30:512:19Running quantized Z-Image GGUF for low VRAMThe creator demonstrates how to use a compressed GGUF version of Z-Image in ComfyUI to generate images on hardware with as little as 4GB of VRAM.ComfyUI · advanced
  45. 37:581:16Applying LoRAs to Z-Image workflowsA demonstration of adding a LoRA node to a Z-Image workflow in ComfyUI to generate specific styles, specifically showing a Commodore 64 pixel art output.ComfyUI · advanced
  46. 12:550:11Structuring prompts in AI Master ProA brief walkthrough of the Prompt Creator tool inside the AI Master Pro dashboard, showing how it breaks down prompts into subject, action, and environment.AI-PRO.org · Nano Banana
  47. 19:121:00Organizing AI generations with Adobe Firefly BoardsThe video shows how to use the Boards feature in Adobe Firefly to reorganize, group, and ideate based on previous image generations in a visual canvas.Adobe Firefly · beginner
  48. 11:080:57Image generation and editing with GrokThe user demonstrates enhancing a plain burger photo into a promotional image and generating a new image of a cat from a text prompt.Grok · Flux · beginner
  49. 2:030:34Generate multiple camera angles with Shots appUsing the 'Shots' app within Higgsfield, the user uploads a single image to automatically generate nine unique professional camera angles of the same character.Higgsfield
  50. 1:330:24Refine and evolve AI images using node connectionsThe demo shows how to use a generated image as an input for a subsequent node in Picsart Flow to refine and adjust the visual while maintaining the original structure.Picsart · beginner · Social Media & Content Creation
  51. 9:382:18Using multiple visual references with Kling 3.0 OmniThe creator shows how to upload up to seven different image references (characters and locations) and tag them in the prompt to guide the AI's generation.Kling AI · Kling · beginner
  52. 3:201:18Generate cinematic images with character and location tagsThe demonstration shows how to use '@' tags to reference saved characters and locations within a text prompt to generate consistent cinematic images in Higgsfield.Higgsfield
  53. 3:410:25Generate aesthetic concepts in MidjourneyThe creator shows Midjourney's ability to produce polished, high-aesthetic single images for mood boards while noting the difficulty in maintaining exact character identity between generations.Midjourney · intermediate
  54. 4:260:14High-volume asset production with Leonardo AIThe demonstration shows Leonardo AI's web interface being used for model training and fast production of social and design assets.Leonardo AI · intermediate
  55. 1:141:59Launching Fooocus on Google ColabThe user demonstrates how to connect and run the Fooocus application using a Google Colab notebook to generate a Gradio live link.Fooocus · intermediate
  56. 3:134:36Configuring Fooocus generation settingsThe demonstration shows how to use the advanced settings in Fooocus, including selecting performance modes (speed vs. quality), aspect ratios, image count, and cinematic styles.Fooocus · intermediate
  57. 7:492:50Generating and viewing AI images in FooocusThe user initiates the generation process, monitors the progress bar, and opens the resulting high-quality images in new tabs to show the output of the Fooocus model.Fooocus · Stable Diffusion · intermediate
  58. 0:141:06Refine image styles using Leonardo.ai Flow StateThe user demonstrates how to use the 'More like this' feature in Leonardo.ai Flow State to narrow down image variations into a specific visual style.Leonardo AI · intermediate
  59. 1:430:40Navigate generation history with Flow State layersThe creator demonstrates how to go back to previous 'layers' or steps in the Flow State process to explore different stylistic directions from an earlier starting point.Leonardo AI · intermediate
  60. 3:110:38Water splash and camera work in Grok ImagineGrok Imagine is demonstrated performing a physics test where it handles water splashes well but struggles with clothing morphing.Grok · beginner
  61. 7:180:53Loading Mocha workflow in ComfyUIThe user demonstrates how to drag and drop a JSON workflow file into the ComfyUI interface to automatically build the Mocha node structure.ComfyUI · Wan · advanced
  62. 13:000:48Configuring Mocha model nodes in ComfyUIThe creator shows how to select the specific Mocha, VAE, and text encoder models within the ComfyUI node dropdown menus.ComfyUI · Wan · advanced
  63. 4:301:17Capturing shots with virtual camera controlsThe user shows how to set focal lengths (from 23mm to 300mm) and aspect ratios to 'take a shot' or render a high-fidelity 2D image from a specific perspective within the 3D world.OpenArt · intermediate
  64. 3:390:36Refine prompts with AI and Describe with AIThe user shows how to use Leonardo's built-in AI tools to improve a text prompt or extract a prompt from an uploaded image to replicate its style.Leonardo AI · intermediate
  65. 7:412:34Advanced editing with Canvas EditorThe tutorial walks through using the Canvas Editor to perform inpainting with masks, outpainting to extend image borders, and merging two images together.Leonardo AI · intermediate
  66. 9:422:36Iterative environment generation with Higgsfield AIThe user demonstrates generating and refining a 3D-consistent apartment location using text prompts and the Higgsfield AI image generator.Higgsfield
  67. 11:081:35Multi-reference image generation with @ symbolsThe user demonstrates generating a complex image by uploading multiple references (lion, jaguar pattern, volcano) and using @ symbols in the prompt to assign specific roles to each reference.Runway · intermediate
  68. 1:180:20Using tag suggestions and prompt barThe video shows the NovelAI interface suggesting specific tags as the user types and demonstrates the prompt length bar filling up.NovelAI · beginner
  69. 2:090:49Adjusting prompt weights with bracketsThe tutorial demonstrates using curly brackets to strengthen tags and square brackets to weaken them, showing the visual difference in the resulting image's hair texture.NovelAI · beginner
  70. 4:320:21Recovering prompts via drag and dropThe video shows how to recover the original prompt and seed settings by dragging a previously saved NovelAI image back into the web interface.NovelAI · beginner
  71. 11:132:02Compose and color grade a scene in HiggsfieldThe demo shows how to combine saved characters and locations into a single scene prompt, generate the image, and apply cinematic color grading and film grain effects.Higgsfield
  72. 0:370:21Building a multi-model image generation workflow in WeavyThe user demonstrates how to drag a prompt node and multiple image AI models (like Flux and Imagine) onto the Weavy canvas and connect them to test outputs from one prompt.Weavy · Flux · advanced
  73. 1:520:16Adjusting model properties in WeavyThe user shows how to open the properties panel for a specific node to adjust settings like aspect ratio and prompt strength.Weavy · advanced
  74. 2:030:57Setting up Flux Kontext in ComfyUIThe creator demonstrates how to load the Flux Kontext model, configure CLIP loaders (T5 and Clip L), and refresh the model manager to ensure all nodes are active in ComfyUI.ComfyUI · Flux · advanced
  75. 29:034:45Automating Multi-Angle Prompts with Array and List NodesThe demonstration shows how to use an 'Array' node to split a single block of text (separated by asterisks) into individual camera angle prompts and then mapping them to a 'List' node for batch processing.Figma · intermediate · Graphic Design & Vector Art
  76. 3:361:26Generate images and video with Adobe Firefly BoardsThe demo shows how to use the 'Boards' feature in Adobe Firefly to generate up to four images at once using Google Nano Banana Pro and then animate them into video clips.Adobe Firefly · Nano Banana · beginner
  77. 6:471:23Concurrent image generation in KreaThe user demonstrates Krea's ability to run an 'infinite queue' of image generations concurrently, allowing for rapid asset creation without waiting for individual tasks to finish.Krea AI · intermediate
  78. 15:190:37Batch image generation in Leonardo AIThe user demonstrates selecting the Nano Banana Pro model in Leonardo AI and setting the interface to generate eight images simultaneously.Leonardo AI · Nano Banana · intermediate
  79. 16:540:38Image generation and prompt exploration in ArtlistThe demo shows the Artlist AI image interface, including uploading reference images and using the explore page to recreate shots from other users' prompts.Artlist · beginner · Social Media & Content Creation
  80. 0:210:17Building node-based AI workflows in Figma WeaveThe video demonstrates the Figma Weave interface where a user connects various AI model nodes and image processing blocks to create a repeatable design machine.Figma · intermediate · Graphic Design & Vector Art
  81. 12:390:21Load GGUF models in ComfyUIThe video shows how to add a 'Unet Loader GGUF' node in ComfyUI and connect it to the LTXV chunk feed forward node for stable model loading.ComfyUI · LTX Video · advanced
  82. 1:393:24Generate images with Flux and Ideogram models in Krea AIThe user demonstrates generating a car with a specific license plate using Flux 1.0, Flux 1.1 Pro, and Ideogram 2.0 Turbo models to compare text rendering and realism.Krea AI · Flux · intermediate
  83. 7:162:33Real-time image generation on Krea AI canvasThe demo shows the real-time generation feature where brush strokes and text prompts instantly create and modify images of a car next to a tree.Krea AI · Flux · intermediate
  84. 2:572:23Advanced image control with Dream Studio (Stable Diffusion)The video shows the Dream Studio interface for Stable Diffusion, demonstrating how to adjust image size, generate multiple variations, and use image-to-image editing to refine a scene.Dream Studio · Stable Diffusion · beginner · Advertising & Marketing Creative
  85. 18:321:19Testing complex text rendering in Kling 3.0The creator tests Kling 3.0's ability to render complex text on a bus timetable, showing both the successful rendering of simple text and the artifacts present in dense text blocks.Higgsfield · Kling
  86. 2:500:37Compare Google Imagen (Nano Banana) modelsThe creator generates images using Google's 'Nano Banana' (Imagen) Standard and Pro models to compare text rendering and physical details.OpenArt · Nano Banana · intermediate
  87. 5:410:59Testing Flux Pro, Max, and Flex modelsThe video shows a side-by-side comparison of the Flux 2 family (Pro, Max, and Flex) by Black Forest Labs performing the same prompt task.OpenArt · Flux · intermediate
  88. 12:080:24Prompt adherence test with Qwen (Quen) ImageThe creator demonstrates Alibaba's Qwen image model, which results in a 3D cartoon style when failing to meet the realism requirements of the prompt.OpenArt · Qwen Image · intermediate
  89. 6:420:59Configure Gemma 2B Text Encoder in ComfyUIThe creator shows how to load the Gemma 2B text encoder model into the ComfyUI workflow and select it from the node dropdown menu.ComfyUI · advanced
  90. 42:090:39Generate images with AI modelsA walkthrough of using the Kittl AI panel to select models like Flux or Ideogram and generate images based on text prompts.Kittl · Flux · intermediate · Graphic Design & Vector Art
  91. 5:561:17Adjust camera angles with Camera ControlA demonstration of OpenArt's camera angle control tool to change the perspective of a generated image, including low-angle and top-down views.OpenArt · intermediate
  92. 3:140:32Configure Stable Diffusion 3.5 models in ComfyUIThe creator shows the specific folder structure within ComfyUI where the SD 3.5 Large model and CLIP files must be placed.ComfyUI · Stable Diffusion · advanced
  93. 3:460:34Launch ComfyUI and load SD 3.5 workflowThe demo shows running the GPU script to launch the interface and dragging the SD 3.5 JSON/workflow file into the control panel.ComfyUI · Stable Diffusion · advanced
  94. 2:451:00Accessing Seedance 2.0 via SeaArt (uArt.ai)The presenter walks through the uArt.ai interface to access the Seedance Pro 2.0 model, showing the project panel, aspect ratio settings, and credit costs.SeaArt · Seedance · beginner
  95. 6:311:10Access SeaArt (SeaDeance) models via BytePlusThe creator walks through the BytePlus playground to access SeaArt 1.5 Pro, demonstrating how to adjust resolution and aspect ratio settings to save credits.Bytesplus · Seedance
  96. 5:391:56Advanced image generation settings in AI StudioThe user demonstrates how to adjust aspect ratio, resolution (4K), and grounding with Google Search to generate a specific image of Pearl Street in Boulder using Google AI Studio.Google AI Studio · Imagen · intermediate · Developer / API
  97. 1:120:31Accessing the BytePlus AI PlaygroundThe creator walks through the steps to find the hidden free access path for SeaDance models on the BytePlus website, including navigating the model list and entering the playground.Bytesplus · Seedance
  98. 6:332:28Navigating the Midjourney Web App and Explore TabNick demonstrates how to use the Midjourney web interface instead of Discord, showing how to use the Explore tab to find inspiration and use existing images as style references.Midjourney · intermediate
  99. 17:032:29Adjusting Style Weight and Aspect RatioNick shows how to use the '--sw' (style weight) parameter to increase the influence of a reference image and the '--ar' parameter to change the output to a poster aspect ratio.Midjourney · intermediate
  100. 19:572:44Image Prompt vs. Style ReferenceA comparison of how Midjourney treats an image as a standard image prompt (pulling pixels/subject) versus a style reference (pulling aesthetic/vibe).Midjourney · intermediate
demobook

Show, don’t tell.

Categories

Video & AnimationImage Generation & EditingSales TechEmail Marketing

About

SubmitAboutPrivacyTermsContact

© demobook.co