Real Dream

Real Dream is a unique AI image generation model that combines dream elements with real details, allowing users to easily create works of art between fantasy and reality. It excels at handling soft light and shadow effects, rich color layers, and surreal scenes, making it an ideal tool for digital art and story creation.

Features

• Dream and reality fusion style: Create a visual effect that combines virtuality and reality to enhance the imagination of the work.

• Light and shadow and color adjustment: You can freely adjust the light effect and color saturation to enhance the appeal of the work.

• Surreal scene generation: Easily create unique scenes in the virtual world.

• Character and background integrated rendering: Support high-quality character and environment fusion, presenting a natural transition effect.

• Multi-resolution output support: Meet various needs such as social media, printing and high-definition display.

Who should use it

• Visual designers and artists: Explore new surreal and dream-like creations.

• Brand design and content marketing teams: Create high-quality images for social media and brand promotions.

• Game developers: Build fantasy-style virtual scenes and characters.

• Science fiction and fantasy creators: Used for concept design, illustrations and visual narratives.

• Multimedia and publishing industry practitioners: Create cover illustrations, promotional posters and visual content.

Recommendations

Default SD 1.5: Use the "DPM++ SDE Karras" or "DPM++ 2M Karras" sampler with only 20 steps for better quality. "DPM++ SDE Karras" has better quality but is slow.

Default SD 1.5: Use the CFG scale between 5 and 9. CFG scale at 5 is recommended. Stable Diffusion default value is 7.

SD 1.5 LCM: Use the "Euler a" or "LCM" sampler with only 8 steps for better quality.

SD 1.5 LCM AND SDXL Lightning: Use the CFG scale between 1 and 2. CFG scale at 2 is recommended.

Pony SDXL: Use the "Euler a" or "DPM++ SDE Karras" sampler with 20-30 steps for better quality.

LCM with DPM++ SDE Karras: Sampling steps 8, Hires. Fix enabled, upscaler latent, Hires steps 2, hires. denoise 0.45, upscale by 1.05, cfg scale 1.5.

LCM with DPM++ 2M Karras: Sampling steps 8, Hires. Fix enabled, upscaler latent, Hires steps 2, hires. denoise 0.55, upscale by 1.05, cfg scale 1.5.

SD 1.5: Resolution between 512 and 768 using "Hires. Fix" or other form of upscaling. The 600x600 resolution is the one that has worked best.

If you use "Hires. Fix", use "Upscale by" with the value 1.5 with denoising at 0.6.

Tips for a better prompt

Use (word) for larger weight and [word] for smaller weight and word:0.5 to set the weight manually.

Recomendations for improvement on performance (Stable Diffusion Web UI)

Use Token Merging Ratio 0.5 on optimization settings.

If you have a GPU with low VRAM, use --medvram or --lowvram on command line arguments (webui-user.bat on Windows).

Enable fp8 in the latest versions of Web UI to save a lot of ram. It can speed up SDXL a lot depending on how much ram and vram you have.

If you are having a lot of trouble running SDXL in the Web UI. Try using Fooocus

Extensions I recommend: Controlnet, Booru tag autocompletion, CivitAI Browser+,Ultimate SD Upscale,Lobe Theme

Recommended negative prompts to improve human images: amputee, deformed body, long neck, extra fingers, bad body proportions, mutated hands, mutilated, mutation, ugly, fused fingers, malformed limbs, extra heads, disfigured,