11:42
AI image generation
Open Art is presented as an all-in-one AI content platform that consolidates dozens of separate AI image and video generator tools into a single place, letting a user generate, upscale, chat-edit, and animate images and photos of real people without juggling multiple separate services.
Using many separate AI generators is described as a "catastrophe": users must jump between windows and sign up for many random services; Open Art bundles these tools in one platform.
Open Art's image generator offers a list of selectable AI image models/"characters" (e.g., Cream 4.0, described as recent and prominent) to generate original images from text prompts.
Generated images can be sharpened via an image upscaler feature offering three AI upscaler models (e.g., Precise Upscale) that convert images to 2K or 4K resolution, shown with a before/after slider.
A "chat to edit" feature lets users modify an existing image conversationally (e.g., "make the cat blue," "make the cat walk") while the AI preserves character consistency.
A separate "edit image" section offers further AI tools: remove objects, expand the photo, stylize it differently, remove/change backgrounds, swap faces, edit people, upscale, and layer blending.
The video generator gives access to over 10 different AI video models, supporting both image-to-video (drag and drop an image) and text-to-video generation with a prompt.
Image-to-video can be done with no extra input at all, or guided with a text prompt describing the desired motion.
AI-generated video still shows visible quirks (e.g., unnatural movement near the edge of a table) regardless of the platform or model used.
A real personal photo can be turned into new scenes, outfits, or a professional headshot (e.g., "a professional headshot of this person wearing a blue suit in New York during sunset") while keeping the person's likeness, and the resulting image can then be animated into a video.
Pricing runs on a credit system: the Essential plan costs $7/month (billed annually) for 4,000 credits; a single image costs 15 credits (~266 images/month), a basic short video costs 100 credits, and a 10-second 1080p video costs 350 credits.
Cream 4.0 — One of the AI image generator models selectable within Open Art's image generator, described as prominent and recently released, used to create original images from text prompts. Apply: In the image generator's model list, select Cream 4.0, enter a text prompt (e.g., "a cat sitting on a table"), set the number of images to create (one image costs 15 credits), and hit create.
Image Upscaler — An Open Art feature offering three AI upscaler models that convert regular images into 2K or 4K resolution. Apply: Open a generated image, click "upscale," choose one of the three upscaler models, and hit create to get a sharper version, viewable via a before/after slider and side-by-side comparison.
Precise Upscale — One of the three specific image upscaler models available inside Open Art's upscaling tool. Apply: Within the upscaler view, select the Precise Upscale model on a chosen image and hit create to sharpen it into a higher-resolution version.
Chat to Edit — A conversational image-editing feature where a user types natural-language instructions in a chat panel to modify an existing image. Apply: Select an image from history, type an instruction such as "make the cat blue" or "make the cat walk," and hit enter; the AI edits the photo while keeping character consistency.
Edit Image toolkit — A dedicated section in Open Art offering AI-based editing tools: remove objects, expand the photo, stylize it differently, remove/change backgrounds, swap faces, edit people, upscale, and layer blending. Apply: Pick an image from history in the edit image section, choose a tool (e.g., "expand" to add surrounding detail beyond the original frame), and generate — demonstrated by expanding a square cat photo to reveal a plant and window while the cat itself stays unchanged.
Image-to-Video generation — An Open Art video feature that converts an existing still image into a short AI-generated video, with or without a guiding text prompt. Apply: Drag and drop an image into the video generator, optionally add a motion prompt (e.g., "a cat walking on the table"), and hit create to produce a roughly 30-second AI video.
Text-to-Video generation — Open Art's video generator provides access to over 10 different AI video generator models that can create video directly from text prompts. Apply: Go to the video tab, choose one of the available video models, type a descriptive prompt, and hit create.
Selfie-to-scene/headshot transformation — A workflow that uses a real photo of a person plus a text prompt to generate new stylized scenes or a professional headshot while preserving the person's likeness. Apply: Drag and drop a personal photo into the image generator, write a descriptive prompt (e.g., "a professional headshot of this person wearing a blue suit in New York during sunset"), set the number of images to generate, and hit create; the resulting image can then be dropped into the video generator to animate it.
Open Art credit/pricing system — Open Art's usage model where each action consumes credits drawn from a monthly plan allowance — e.g., 15 credits per image, 100 credits for a basic short video, and 350 credits for a 10-second 1080p video, under an Essential plan of $7/month (billed annually) for 4,000 credits. Apply: Check the upgrade/pricing page to choose a plan, then budget usage by comparing per-action credit costs (images vs. video length/resolution) — e.g., 4,000 monthly credits allow about 266 images at 15 credits each.
The video frames Open Art's core value as consolidation rather than superior AI quality: the pitch is explicitly about eliminating the need to "jump between all these windows and sign up to these random services with weird names."
Character/subject consistency is emphasized as a differentiator — after editing, it's "clearly the exact same cat," and person-based edits keep the same face, implying the platform is being sold on identity preservation across edits, not just raw generation.
The selfie-to-headshot workflow is framed as a practical replacement for professional photography ("you don't need to hire a real photographer anymore"), not just a novelty demo.
The presenter openly concedes a platform-agnostic limitation mid-demo — unnatural motion near the table's edge — stating this happens "no matter which platform you use and no matter which model you use," which is a caveat volunteered by the source itself rather than glossed over.
Credit costs scale steeply for video versus images: a single higher-resolution 10-second video (350 credits) costs over 20x more than a single image (15 credits), so heavier video use can burn through a monthly plan much faster than image use.
The video's title ("Goodbye Higgsfield") positions Open Art as a replacement for the competing platform Higgsfield, even though Higgsfield itself is never mentioned or discussed within the transcript content.
«This is a catastrophe. You need to jump between all these windows and sign up to these random services with weird names all the time.»
— 00:13
«So, no matter which platform you use and no matter which model you use, you still have some AI quirkiness like this.»
— 08:11
«So you don't need to hire a real photographer anymore.»
— 09:33
«I mean, isn't that incredible?»
— 07:23
«if I want to create a simple short video like this, it will cost 100 credits»
— 10:48
Reception
Audience shows moderate engagement with constructive questions and one positive mention of the product, but overall enthusiasm is muted.
The video is a straightforward, promotional-style feature walkthrough of Open Art (complete with a discount code) that demonstrates real breadth — generation, upscaling, chat editing, image-to-video, and person-based transformations — while transparently flagging the credit-cost tradeoffs of video versus images and admitting lingering AI video artifacts.
11:42