![<lora:add_detail:0.8>, <lora:astronomy_wallpapers01:1>, detailed background cyberpunk, masterpiece, detailed, colors(black and white:1.2)and violet, scene, portrait, face closeup, mouse, realistic fur, detailed eyes, <lora:gachaSplashLORA_v40:1>, [[by kenket|by totesfleisch8], by thebigslick:by silverfox5213:0.8], [by syuro, by paloma-paloma:0.2]](https://go_service.aieasypic.com/?url=https%3A%2F%2Fimage.civitai.com%2FxG1nkqKTMzGDvpLrqFT7WA%2F0262bb57-ac78-4eb5-9c42-d8b66f7ce883%2Fwidth%3D600%2F2634434.jpeg&type=jpeg&width=512&quality=80)
Quick Generate
Model Description by Creator
Coconut furry mix 2
New version of coconut mix. Models adequately perceive the prompt for both furry models, and for anime, and for classic SD. The model is very responsive to prompts, so you don’t have to fiddle with the weight to get it to do what you need. Produces decent animations with the AnimatedDiff module.
Examples:
Coconut furry mix 2 vivid
Improved version of Coconut furry mix 2. Adds more details and rich colors, making the artwork brighter. This model also works well with Improved Humans Motion Module to create animations.
Examples:
Coconut furry mix 2 gentle
Improved version of Coconut furry mix 2. An alternative version is not as colorful like vivid, but draws in softer colors, the characters look more cute. Good at rendering clothes but a little bit lewd, it's can forget underwear). This model also works well with Improved Humans Motion Module to create animations.
Examples:
Coconut furry mix 2 hardlines
Improved version of Coconut furry mix 2. An alternative version draws well the border of characters and objects, suitable for drawing in the style of anime or comics. The model is also suitable for normal generation, but the anime style and linеart is better. This model also works well with Improved Humans Motion Module to create animations.
Examples:
Recommended settings: DPM++ 2M SDE Karras, 20-120 steps, 768x512 or 960x540, CFG Scale 3-7, Hires.fix 4x_foolhardy_Remacri or LDSR, Denoising strength 0.35-0.45, SD VAE vae-ft-ema-560000-ema.safetensors
For animations: Steps: 60 and higher, Sampler: DDIM, CFG scale: 7-9, Size: 512x512 or 768x512, VAE: vae-ft-ema-560000-ema-pruned.safetensors, 'motion_module': 'improvedHumansMotion_refinedHumanMovement.ckpt', 'video_length': 32, 'fps': 8
P.S. If you can find better settings for the animation, I'd appreciate it if you could let me know. My video card is too slow for animation, which closes the way to experimentation.
Don't forget to read my guides:
"How to make your prompt great again" - A realistic upscaling guide has also been prepared for this model.
"Mr Prompters" - also for this model, a helper bot was written for SillyTavern, which will help you write a prompt if you are a happy owner of a GPT-4 key.
"How to make your generations great again" - Acceleration of generation to cruising speed and other little things guide.
