Go to year: 2022 • 2023 • 2024 (pt 1) • 2024 (pt 2)
Introduction
This article covers the second part of 2024 from August through December. During this period, multiple models of Flux were released as well as updates to Stable Diffusion 3.
Prompts and project details can be found at the bottom of the article. High resolution versions of the comparison image grids are in this article's attachment.
The Models
Flux Pro 1
August 2024
The Pro models are Flux's most detailed and precise offerings, but they aren't available for download to regular users. Many sites offer the Pro models for online generation. They can produce legible text and follow positioning instructions.
❌free download
Flux Dev 1
August 2024
The Dev model is available as a free download. This model is less detailed than the Pro version, but still produces high quality images and legible text.
✅free download (civitai)
Aura Flow 0.2
August 2024
AuraFlow 0.2 was released shortly before version 0.3. Unfortunately, it requires 24gb VRAM (I have 16) to run locally and I can't find any sites hosting this version. If anyone knows where I can try it online or can run it locally and is willing to run my test prompts for me, please let me know.
Aura Flow 0.3
August 2024
AuraFlow is available as a free download. I haven't had much time to delve into it yet.
✅free download (civitai | huggingface)
Ideogram 2
August 2024
Ideogram 2 can create more detailed and realistic images than version 1. It can produce legible text and follow detailed instructions.
❌free download
Imagen 3
August 2024
Google's Imagen 3 does an excellent job of following prompt instructions and rendering legible text. It seemed overly restrictive with its prompt censorship and forced me to rewrite prompts that all the other models I tested accepted (for example, "woman lying on the grass" had to be changed to "woman sitting on the grass").
❌free download
Flux Pro 1.1
October 2024
Flux released an update to their Pro model.
❌free download
Omnigen v1
October 2024
Omnigen says this "is a unified image generation model that can generate a wide range of images from multi-modal prompts". Using the default settings in the online generator, the images looked extremely smooth and it isn't good with text or following positioning instructions.
✅free download (civitai | github)
Stable Diffusion 3.5 (Large)
October 2024
Stable Diffusion 3.5 offers significant improvements over 3.0, though we only got the medium version of 3.0. Overall image quality is better and it's good at rendering text and following prompt instructions. It still has problems with anatomy sometimes.
✅free download (civitai | huggingface)
Stable Diffusion 3.5 (Medium)
October 2024
A less resource intensive version of 3.5. It's capable of rendering legible text and following detailed instructions, but had more problems with anatomy than the large version.
✅free download (civitai | huggingface)
Recraft 3
October 2024
This model is good at rendering legible text, following prompt instructions, and artistic compositions. Unfortunately, it's a censored model that seems prone to wrongly flagging prompts as NSFW. It absolutely refused to accept any variation of my cyberpunk prompt so I'm stuck with including the error message it shows instead.
❌free download
Flux Ultra 1
November 2024
This Flux model is capable of generating 4k images, which are 4 times higher than its previous versions. It also offers a "raw mode" for more authentic looking images.
❌free download
Project Details
Disclaimer
I'm not an insider with special access to anything or a programmer who understands how all this works under the hood. I took some time to research, but this is from information found online and I can't guarantee everything is accurate. This is a work in progress; I'm still working on filling in missing information.
Also note that this is only a comparison of base models. Some models can produce significantly better images by using trained checkpoints, styles, presets, or detail enhancers.
Criteria
Must still be publicly accessible in 2024 without a complicated setup.
For this series, I've excluded turbo/fast versions of the models.
Process
I chose 15 prompts that show a variety of photo realism, art styles, people, animals, objects, specific instructions, open-ended short prompts, text, and abstract concepts.
All images come from the first generation set and I never picked from more than 1-4 images.
When possible, I used images from the same seed which can show differences between minor versions of the same model.
I used the recommended settings for each model or the default offered online.
I didn't use additional styles or presets.
Prompts
african hydropunk princess
artificial intelligence
astronaut exploring an alien planet
overhead view of a breakfast plate with eggs, toast, strawberries, coffee, and a fork
exterior of a cafe watercolor painting
person wearing cyberpunk accessories in a high tech neon city
druid man character design
ethereal fairy in the style of oil painting
graphic design logo with fennec fox and succulents and text "Desert Design"
man and a woman in love
photo of a deer in an enchanted forest with cinematic lighting
Photo portrait of a woman with long black curly hair in natural light. She's wearing a fashionable purple blouse, a gold necklace with a locket, and hoop earrings. Bokeh background.
pixel art city street scene with shops and pedestrians at night
red potion bottle with text "health" on the left, blue potion bottle with text "mana" in the middle, green potion bottle with text "poison" on the right, on a wooden table in a dark alchemist's laboratory, in the style of a detailed digital painting
woman lying on the grass
Article Updates
Nov 26, 2024: Added missing Recraft 3 image and updated the attachment.
Nov 26, 2024: Added download links.
Go to year: 2022 • 2023 • 2024 (pt 1) • 2024 (pt 2)