DreamShaper v8
Model specifications
DreamShaper V8, created by Lykon, is a Stable Diffusion model fine-tuned on runwayml/stable-diffusion-v1-5, released in October 2024. Designed as an open-source alternative to proprietary models like MidJourney, it aims to be a “does it all” solution, blending photorealism, anime, and illustrative art with high quality.
On NightCafe, DreamShaper V8 supports runtime options (Short, Medium, Long) and aspect ratios (1:1, 16:9, 9:16, 3:4, 4:3), excelling in creating detailed portraits, fantastical scenes, and vibrant illustrations. It uses the DEISMultistepScheduler with 25 inference steps for balanced speed and detail, though it may struggle with photorealism or anime compared to specialized models.
Ideal for artists, hobbyists, and marketers, DreamShaper V8 offers NightCafe users creative flexibility, with strong community support.
Frequently asked questions
What is DreamShaper V8?
DreamShaper V8 is Lykon’s versatile AI model, fine-tuned from Stable Diffusion for high-quality art, photorealism, and anime-style images.
What types of images can DreamShaper V8 create?
It generates artistic illustrations, photorealistic portraits, and anime visuals, supporting aspect ratios like 1:1 and 16:9 for diverse creative tasks.
How do runtime options affect DreamShaper V8?
Short, Medium, and Long runtimes on NightCafe adjust processing depth, with Long producing the most detailed, vibrant images.
Is DreamShaper V8 suitable for beginners?
Yes, its intuitive NightCafe interface allows beginners to create stunning visuals with descriptive prompts, no advanced skills needed.
What are DreamShaper V8’s limitations?
It may not match specialized models in photorealism or anime and can misinterpret complex prompts, requiring prompt refinement.
A once respectable model now stripped down to nothing but errors only! Think it's high time we remove this and ALL incident models from the site now.
DreamShaper used to be great but it’s doing a terrible job at following prompts. The prompt I gave was: “wide-angle lens, panoramic view. 8k resolution. DSLR. A enormous orange and deep red colored glass rose in bloom floating in front of a cosmic backdrop in outer space, surrounded by stars, nebulae, planets and suns. Highly detailed stars and nebula. Photorealism.” It’s revised prompt was “ Photorealism. Medium shot. A enormous orange and deep red colored glass rose in bloom floating in front of a cosmic backdrop in outer space, surrounded by stars, nebulae, planets and suns. Wide-angle lens. Cosmic explosion of colors. Glowing stellar lights. Vibrant nebula clouds. 8k resolution. Highly detailed. Best quality. Cinematic film still.” The images it generated will be in my reply below⬇️
This sucks. I thought something strange was going on because it was charging so many credits to use it. And the results were bad. What's the deal?
It great for Fantasy type art, But has trouble with sci-fi type art, It works well with Steampunk type art. =D Overall it a good base model to use.
My favorite model to use! I make a big batch of images until it says I'm creating too fast, delete the ones I don't want, then evolve the best ones to XL Lightning for images of my characters I never would've been able to make without AI. It can be a bit muddy if you don't evolve to another model but nothing else follows my prompts nearly as well. For costing zero credits, it's absolutely awesome! 💖
I would like to see how this model was trained. Based on this, I could improve what I could create with more assertiveness.
I asked to create "Wide open mouth" and I got this lol.... It`s crazy 🙈
Comments