- 20 Posts
- 41 Comments
Joined 1 year ago
Cake day: October 1st, 2023
You are not logged in. If you use a Fediverse account that is able to follow users, you can follow this user.
1·1 year agoSwan, eagle, bull twice… yeah. Fish seems right up his ally.
Donkey, the donkey-nosed donkey.
Bare in the streets, bear in the sheets.
I’m a big fan of natural majiks and druidic mysticism.
He knows what you’ve been thinking, he knows when you’re alone,
he knows if you’ve been bad or good, and he might just take your bones.
Is this what’s known as “family” dinner?
Someone appreciates lighting in their prompts. I’m a big fan of adding ‘subsurface scattering’, ‘x colour highlights’/midtones/shadows, for precise lighting control, brown and tan are wonderful lighting colours.
Try adding: holding food draped in cloth made of melted cheese
A Christmas Vision
spoiler
Stable Diffusion
Prompt:
neonpunk style concept art long shot scenic professional photograph of cinematic film still ethereal fantasy concept art of (masterpiece:1.2), (best quality:1.2),RAW photo, 8k uhd, dslr, natural lighting, maximum fidelity, ultra high detail, ultra HD, Panavision Millennium DXL2 8k Photo (1 beautiful eye, ornate silver eyelashes, reflective metal, santa, christmas tree). shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, photo-realistic, raw photo, amateur photography, realism, maximum detail, cinematic bokeh, GhostlyStyle , bright, warm, colourful, christmas, santa's salve pens, SDS_Particle_Flow watce, snow, ice, cold, freezing, . magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy . shallow depth of field, vignette, highly detailed, high budget Hollywood movie, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy, perfect viewpoint, highly detailed, wide-angle lens, hyper realistic, with dramatic sky, polarizing filter, natural lighting, vivid colors, everything in sharp focus, HDR, UHD, 64K . digital artwork, illustrative, painterly, matte painting, highly detailed . cyberpunk, vaporwave, neon, vibes, vibrant, stunningly beautiful, crisp, detailed, sleek, ultramodern, magenta highlights, dark purple shadows, high contrast, cinematic, ultra detailed, intricate, professional
Neg:
(worst quality:1.2), (low quality:1.2), (normal quality:1.4),(hair ornament), (cropped:1.4),badhandsv5-neg, badhandv4, NegfeetV2, bad_prompt_version2, By bad artist -neg, ng_deepnegative_v1_75t, bad_pictures, BadDream, UnrealisticDream, By bad artist anime -neg, badquality-neg, BadNegAnatomyV1-neg, bad-picture-chill-75v, lowres, lowres graffiti, monochrome, grayscale, sketches, bad anatomy, bad hands, twisted hands, extra fingers, fewer fingers, missing fingers, strange fingers, fused fingers, malformed limbs, redundant limbs, redundant fingers, error, ((extra nipples)), blurry, deformity, deformed hand, extra limbs, aged up, age spot, wrinkled skin, wire, skin spots, freckle, skin blemishes, stain on face, mole, dark mole, ugly, fat, acnes, nevus, nasolabial folds, text, extra digits, fewer digits, jpeg artifacts, signature, watermark, username, censored, photographic, realistic, realism, 35mm film, dslr, cropped, frame, text, deformed, glitch, noise, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, sloppy, duplicate, mutated, black and white, anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, photo, photorealistic, realism, ugly, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured
Params:
Steps: 50, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2280256292, Face restoration: GFPGAN, Size: 768x512, Model hash: 4199bcdd14, Model: revAnimated_v122EOL, Denoising strength: 0.2, Clip skip: 2, ADetailer model: face_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer model 2nd: Eyes.pt, ADetailer confidence 2nd: 0.3, ADetailer dilate erode 2nd: 4, ADetailer mask blur 2nd: 4, ADetailer denoising strength 2nd: 0.4, ADetailer inpaint only masked 2nd: True, ADetailer inpaint padding 2nd: 32, ADetailer version: 23.11.1, ControlNet 0: "Module: recolor_luminance, Model: control_v11p_sd15_inpaint [ebff9138], Weight: 1, Resize Mode: Crop and Resize, Low Vram: False, Threshold A: 1, Guidance Start: 0, Guidance End: 1, Pixel Perfect: False, Control Mode: Balanced, Save Detected Map: True", Hires prompt: "(masterpiece:1.2), (best quality:1.2),RAW photo, 8k uhd, dslr, natural lighting, maximum fidelity, ultra high detail, ultra HD, Panavision Millennium DXL2 8k Photo (1 beautiful eye, ornate silver eyelashes, reflective metal, santa, christmas tree). shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, photo-realistic, raw photo, amateur photography, realism, maximum detail, cinematic bokeh, GhostlyStyle , bright, warm, colourful, christmas, santa's salve pens, SDS_Particle_Flow watce, snow, ice, cold, freezing,", Hires upscale: 2, Hires steps: 12, Hires upscaler: 8x_NMKD-Superscale_150000_G, Lora hashes: "SDXLGhostStyle: 26aaca0abd6c, theTalosProject_v11: 55f90e8cf7e3, Loraeyes_V1: da8286d2ab99, add_detail: 7c6bad76eb54, detail_slider_v4: 8347b7ec221e, zoom_slider_v1: 22e65bb05fb3, SDS_Particle_Flow: 8859996b890a, watce-sdxl: 5ceb29ddb464", Version: v1.6.0-2-g4afaaf8a
Star Wars: Battlefront 2 now with Sailor Moon micro transactions.
Glad you’re enjoying my work, I appreciate the link back!
AI can’t count, hence the problem.
You tell an AI you want 5 of something, it looks at all the reference that it has on what “five of something” looks like, then guesses.
If we could teach these predictive engines to recognise fixed notation like numbers it would be so much easier, but the training data would still lack nuance in it’s descriptors.
How often do people talk about how many fingers are showing in what position their hand is when posting a photo? Or how many toes their chicken’s feet have?
That’s unfortunate since it’s just images linked in the post body.
That’s really cool to know, thanks! You can cover a lot of ground using tools like that, probably excellent for creating training data.
The software I use is called Stable Diffusion, it’s a Python based FOSS AI image generation software. It uses a local web interface to interact with the program, the one I use is called automatic1111 or a1111 for short. A1111 can be loaded with different extensions that add pre and post-processing tools. You can also access free community made resources and make online gens at civitai.com, it’s free to start an account and if you want I can give you a referral link. From there you download gigabytes worth of base models and training data packages called ‘lora’ which you can load into Stable Diffusion. You can find different training data to make it easier to generate the specific things you want. From there you choose what resources you want to use, build your prompts for what you want, build a negative prompt to remove the things you don’t want, and play with the various configuration settings in Stable Diffusion while generating images testing to get the intended image.
This is what my interface looks like:
And each of those tabs across the top are different tools for pre-and post processing.
Maybe an hour of playing with that base model and my loras to hit the style, the rest took all of 20 mins.
As soon as I find a manufacturer, marketer, and angel investor.
I appreciate her feedback, I think she has fantastic taste!
It’s actually running light on the checkpoints and loras for some of my gens. But heavy on the style keywords. I think my record is 23(?) different resources.
spoiler
Prompt:
neonpunk style cinematic photo breathtaking Masterpiece, maximum fidelity, ultra high detail, ultra HD, Panavision Millennium DXL2 8k photograph of a (erotic neonpunk transparent glass combat armor led lit, red black yellow), transparent, led lit, glass bra , cyberpunk neonpunk, . 35mm photograph, film, bokeh, professional, 4k, highly detailed . cyberpunk, vaporwave, neon, vibes, vibrant, stunningly beautiful, crisp, detailed, sleek, ultramodern, magenta highlights, dark purple shadows, high contrast, cinematic, ultra detailed, intricate, professional, ((award winning,full body photo of person,)), (8k, RAW photo, best quality, ultra high res, photorealistic, masterpiece, ultra-detailed, Unreal Engine),highres, masterpiece , Photo, (sharp focus:1.2), (realistic:1.3),(photorealistic:1.3),ultra-detailed, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, Fujifilm XT3, best quality, beautiful lighting,cinematic lighting , depth of field. 4K, HDR. by (Jeremy Lipking:1.1)Neg:
(worst quality:1.2), (low quality:1.2), (normal quality:1.5), (cropped:2), (hair ornament:2), (censored:1.3) film grain, excess noise, amateur, (blurry:1.3), (script, inscription, logo, watermark, signature, title, attribution, text, words:1.5), cropped, out of frame, (worst quality, low quality, poor quality), jpeg artifacts, poorly lit, overexposed, underexposed, glitch, error, out of focus, soft textures, low resolution, low fidelity,(ghibli grain,semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, digital art, anime, manga:1.5), badhandsv5-neg, NegfeetV2, By bad artist -neg, ng_deepnegative_v1_75t, bad_pictures, BadDream, UnrealisticDream, badquality-neg, BadNegAnatomyV1-neg, bad-picture-chill-75v, (breast obfuscation, nipple cover, under shirt, bra, hidden nipples, hidden breasts, opaque:1.3), cop radio, teeth-lips, lowres, lowres graffiti, monochrome, grayscale, sketches, bad anatomy, bad hands, twisted hands, extra fingers, fewer fingers, missing fingers, strange fingers, fused fingers, malformed limbs, redundant limbs, redundant fingers, error, ((extra nipples)), blurry, deformity, deformed hand, extra limbs, text, extra digits, fewer digits, jpeg artifacts, signature, watermark, username, censored, ugly, grainy, drawing, painting, crayon, sketch, graphite, impressionist, noisy, (blurry:1.3), soft, deformed, ugly, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured, drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfiguredParams:
Steps: 55, Sampler: DPM++ 2M Karras, CFG scale: 6.5, Seed: 4001740907, Size: 768x1024, Model hash: b3ac00bd4f, Model: sdxlUnstableDiffusers_v8HEAVENSWRATH, Variation seed: 2449762083, Variation seed strength: 0.05, Denoising strength: 0.2, Clip skip: 2, ADetailer model: face_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer restore face: True, ADetailer ControlNet model: control_v11p_sd15_inpaint [ebff9138], ADetailer ControlNet module: inpaint_global_harmonious, ADetailer model 2nd: Eyes.pt, ADetailer confidence 2nd: 0.3, ADetailer dilate erode 2nd: 4, ADetailer mask blur 2nd: 4, ADetailer denoising strength 2nd: 0.25, ADetailer inpaint only masked 2nd: True, ADetailer inpaint padding 2nd: 32, ADetailer ControlNet model 2nd: control_v11p_sd15_inpaint [ebff9138], ADetailer ControlNet module 2nd: inpaint_global_harmonious, ADetailer version: 23.11.0, Hires upscale: 2, Hires steps: 16, Hires upscaler: 8x_NMKD-Superscale_150000_G, Lora hashes: "Glass: 34325be36a2a, breastsizeslideroffset: ca4f2f9fba92, age_slider_v6: 496534b2472f, AdvancedEnhancerXLv2: 4bd93e82ba85, PeachFuzz: 263f53081046, f412glass_base_c: 228287ed458e, GlassDevice: bf9e7289a826", ControlNet 0: "Module: inpaint_global_harmonious, Model: control_v11p_sd15_inpaint [ebff9138], Weight: 1.0, Resize Mode: ResizeMode.INNER_FIT, Low Vram: False, Guidance Start: 0.0, Guidance End: 1.0, Pixel Perfect: True, Control Mode: ControlMode.BALANCED, Save Detected Map: True", Version: v1.6.0-2-g4afaaf8a, Hashes: {"embed:BadDream": "758aac4435", "embed:BadNegAnatomyV1-neg": "b389c1e5f9", "embed:By bad artist -neg": "2d35613490", "embed:NegfeetV2": "df90b1ff66", "embed:UnrealisticDream": "a77451e7ea", "embed:bad-picture-chill-75v": "7d9cc5f549", "embed:bad_pictures": "522ac70ba9", "embed:badquality-neg": "3f15e4aefd", "embed:ng_deepnegative_v1_75t": "54e7e4826d", "lora:Glass": "b0838dc7bb", "lora:AdvancedEnhancerXLv2": "6e8beb025f", "model": "b3ac00bd4f"}