PirateDiffusion is a pirate-themed (harr-harr) AI image creation bot. No piracy going on here, don't get it twisted. You can use our bot to make pretty things. Activate your bot and try these examples below.
1. The picture, made with eventhorizon3-krea2
/workflow /run:eventhorizon3-krea2 /size:1280x1280 /images:3 portrait of a beautiful pirate woman, green hair, canadian, freckles, making a flirty expression. she is typing on a laptop with a skull and crossbones glowing on the back, in a tavern full of drunk parrots and godzilla. on the laptop there's a label "Baddie's" in crisp legible large letters
2. In Telegram, right-click (or long-press) the picture the bot sent and choose Reply, then send the next command as that reply. The reply tells the bot which picture to animate.
3. The video, animated with animate-h3
/wf /run:animate-h3 a lively pirate tavern scene with fluttering parrots flying midair hovering and a beautiful pirate woman, the camera pans around her slightly as she leans slightly and winks at the viewer, turning her head, in the background a lively set of customers are waving and screaming and hollering
After you've activated your bot, copy this command to generate a similar video.
wan2.2-i2v-high-Screen Flood（屏幕淹水）
/workflow /run:video-wan22 <high-screen-flood-wan> then water suddenly rushes up from the bottom and submerges the entire screen.
Works best with an image input: reply to a picture and use /run:animate-wan22 instead.
Wan · LoRARender by jeh88615 via BunchaPrompts
/workflow /run:dasiwa-h3 <exposure-slider-h3> A realistic candid handheld video in a city square. A woman sits on a bench eating a small snack while a pigeon stands directly in front of her staring intensely at the food. She slowly moves the snack away, and the pigeon follows it with its eyes. She moves it left, then right, and the pigeon tracks every movement with exaggerated seriousness. She eventually gives the pigeon a tiny piece and it immediately walks away as if nothing happened. Natural daylight, realistic bird movement, subtle handheld camera shake, deadpan comedy, ordinary everyday environment.
Tip: The prompt is text-to-video, but it also works when you supply your own image. In that case, first paste a photo into your bot (leave the compression check on) then reply to a picture and use /run:animate-dasiwa-h3 instead of /run:dasiwa-h3. Animate means image-to-video (I2V).
H3 · LoRA
Render by alcaitiff via BunchaPrompts
Pixel Art Animation (Birdman Style) I Wan 2.1 I2V LoRa
/workflow /run:video-wan21-turbo <birdman-pixelart1p5-wan> p1x3lStyl3 animation, pixel art, a video of a 2D video game. a blue robot and a C1VCH@N maid are fighting. They punch and kick each other. The maid blocks the robot's punches and the maid does a flying spinning kick. pixel art, fighting game, video game, smooth animation. The camera is steady. The scene is computer generated.
Works best with an image input: reply to a picture and use /run:animate-wan21-turbo instead.
Wan · LoRARender by BrokenB via BunchaPrompts
Each picture is one /render command: the model's ModelTrends ShortCode, the render's own settings and the prompt.
/render <revani2> /size:540x860 /steps:26 /guidance:7 /seed:2897627118 /sampler:dpm2m /karras most cute fantasy animals of the world,different species,eevee based,big eyes,very fluffy,, best quality,masterpiece,realistic,masterpiece,Highly detailed,extreme detail description,extremely detailed CG unity 32k wallpaper,8k
SD15 · ModelRender by albert1 via BunchaPrompts
/render <counterfeit3> /size:512x1024 /steps:25 /guidance:10 /seed:1293666383 /sampler:dpm2m /karras /clipskip:2 (masterpiece, best quality),1girl with long white hair sitting in a field of green plants and flowers, her hand under her chin, warm lighting, white dress, blurry foreground
SD15 · Model
Render by rqdwdw via BunchaPrompts
/render <detail-tweaker-xl> /steps:31 /guidance:7.5 /seed:287430763 /sampler:dpm2m /karras /clipskip:2 Porcelain Mix Gold Style Pony, Masterpiece, score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, pmg style, masterpiece, best quality, a nice piggy bank made of porcelain, 19th century style
SDXL · LoRARender by varnaart via BunchaPrompts
Install Telegram, open the bot and press Start.
The bot renders on a GPU service. You connect your account inside the bot, once.
Copy a command from a card, paste it in the chat and send it. Then change the prompt, the ShortCode or a parameter and send it again.
Thousands of models are preloaded. Each ShortCode below names one of them; the command is a real prompt to start from.
/render <illustrious2-xl> /steps:28 /guidance:4.5 /seed:2353079513 /sampler:k_euler_a masterpiece, best quality, stylized, 1girl, solo, blonde hair, wavy hair, half updo, sidelocks, choppy bangs, blue eyes, light smile, open mouth, looking at viewer, hand up, holding bottle, aqua thermos, visor cap, pink cap, transparent cap, t-shirt, white shirt, cropped jacket, denim jacket, black backpack, upper body, from below, dutch angle, blue sky, day, cloud, bird [[worst quality, low quality, displeasing, lowres, bad hands, mutated hands]]
SDXL · Model
Render by Dajiejiekong via BunchaPrompts
/render <wildcard-ogfusion-xl> /size:896x1152 /steps:30 /guidance:5 /seed:2667752565 /sampler:dpm2m /karras concept art hidden face, mysterious, hooded, full body, dark enigmatic warrior, standing, storm of falling shards, glowing ethereal giant heavy thick sword in hand, warrior’s intricate armor, tattered cloak that billows in the wind, atmosphere is charged with an otherworldly energy, fantasy realism, dramatic lighting, detailed textures to bring the scene to life, , , . digital artwork, illustrative, painterly, matte painting, highly detailed
SDXL · ModelRender by DreamCk via BunchaPrompts
/render <vast-expanse-krea2> /steps:10 /guidance:1 /seed:1422175916 /sampler:k_euler DCVSTEXP. dcd@rkf@ntsy. Aerial wide shot of a colossal throne carved from a mountain range, its seat as wide as a valley, a river running across the seat and falling off its front edge as a waterfall, a tiny caravan of camels crossing one armrest. Orange campfires along the caravan, haze drifting between the peaks, the sky deep night blue. Overwhelming scale, deep spatial layering. Crushed blacks, orange and cobalt blue, painterly 1970s dark fantasy book cover, heavy film grain.
Krea2 · LoRARender by veryslowlearner via BunchaPrompts
The render command, ModelTrends ShortCodes, parameters, weights and negatives, LoRAs, and the video and music workflows, each with a live example.
How to prompt →PirateDiffusion is a Telegram app created by Tlack305 for making images, video and music with slash commands. Each command names a model by its ShortCode, so the same prompt can be tried on any of the thousands of preloaded models.
Commands · Guides · Prompt Gallery · Support · Read the full guide
Make a character once, save the picture as a nickname, put the same person in new scenes with Omni, then animate a still with animate-h3 or animate-ltx25. Real renders, clips and every command.
A Skill is a focused, simple app (or Telegram/Discord command) that does one thing well. No complicated menus or advanced settings. Just describe what you…
There are various AI music models in our system, such as Ace Step XL and Heart Mula.