Category: Text to image
-
Wan 2.2 Lora Workflow
Generating images with a LoRA, generating a custom voice and combining them both to create a talking avatar video. All using AI models available on fal.ai. Using a Wan 2.2 Lora InstaGirlv2 went viral on X.com with its realistic images. The official LoRa is available on Civitai but I found it easier to use on…
-
Qwen Image LoRA
I created a Qwen Image LoRA for creating what I call a “twilight bloom” effect. Sunset with flowes. This image was created using the LoRA: Trained on 15 images I had created on Ideogram. All the images had between 15 and 100 likes and were of a similar style. The training was done on fal.ai…
-
Google Imagen 4 Ultra
Create visual scroll stoppers. Google’s Imagen 4 creates images from your words. It is the most advanced model right now and can handle a lot more text than other models. Tell it to write your flash sale on a neon sign. Tell it to put your best testimonial on a billboard. Turn your tip of…
-
Can generative AI outperform humans in visual marketing content?
Yes, generative AI can help advertisers produce marketing content not only faster, but orders of magnitude cheaper, and at impressive effectiveness levels according to a study. Three studies were conducted. The first study showed the best AI models can outperform human-made marketing visuals across three important perceptual dimensions: quality, realism, and aesthetics. The report even…
-
Flux: A New Frontier in Text-to-Image Generation
Black Forest Labs has unveiled Flux, touted as the most advanced text-to-image model to date. The company aims to establish itself as the industry benchmark for generative media, leveraging the expertise of key developers behind Stable Diffusion technology. Model Variants Flux is available in three distinct versions: Key Features Technical Specifications Performance Claims Black Forest…
-
Midjourney, “sref” and IP-Adapters
Midjourney’s style reference, has sent the AI community into a frenzy with its cryptic “sref” codes promising innovative styles. Yet, a closer inspection reveals the secret sauce isn’t so secret. The kicker is that you don’t even need Midjourney to use these styles – and that changes everything. Enter the IP-Adapter. This powerful algorithm takes…
-
AuraFlow – open source text-to-image
AuraFlow is a new open-source text-to-image model that has the potential to become the new backbone of image creation workflows such as with ComfyUI. Backed by Fal, it has released a base version 0.1 with the promise of more to come. It’s a 6B parameter model, which is quite large, and some are complaining that…