glass and gem infused hawk shaped mask photorealistic green pink theme
Wow, this looks gorgeous! I love the gems and glass design.
Here’s an image of my own. Of course I’m excluded from being able to win. I just like to participate.
Prompt: cyberpunk style, illustration, panoramic shot, Cyberpunk traditional pagan mask, worn by shopkeeper, shopkeeper is leaning on the counter, in an antiquities store --stylize 75 --v 5.2 --ar 4:3
Dalle using chatgpt:
Black and white close-up photo of the king of autumn's mask. The moss, twigs, and feathers are displayed in intricate detail, revealing the texture and patterns. The mask's elements seem to come alive, with every strand of moss and feather visible, giving a sense of depth and dimension.
You can only submit one image for the challenge. As much as I like both of them, could you please remove one?
You can post the removed one as a reply to your original comment if you still like to show it off, that’s fine. The original comment will be the one that counts for the challenge.
Ah didn't know! Thanks I'll remove one!
Bing prompt: post apocalyptic world setting, steam punk mask made with bronze and silver trimming, a worn out top hat with a mouse coming out of a door near the top
Hard choice between two it made, but I'm going with this one.
Too bad the mouse didn't come out the door, that would've been cute to see.
Though I shouldn't complain, this one is very cute as well :)
Here's the one it got right. The mice are weirdly cute. Funny enough this was also the other one I was conflicted about starting with.
Aww, there he is! Mice are cute in general, as long as they don't invade your house :)
I can see why you chose the first one though, it looks more like an actual mask.
Local stable diffusion install:
Faberge, demon, Satan, evil, circuit, cyberpunk, ornate, jewel encrusted, gold, velvet, pointy, opulent, elegant, cybernetic Steps: 40, Sampler: Heun, CFG scale: 17.5, Seed: 1568385646, Size: 768x768, Model hash: 99fd5c4b6f, Model: seekArtMEGA_mega20, Denoising strength: 0.1, Hires upscale: 2, Hires upscaler: R-ESRGAN 4x+ Anime6B
The matching body armor:
Sorry for the low quality, i´ve found no other way to upload animations directly to lemmy, yet.
Edit: Here is a link to a sharing Portal with a higher Resolution GIF :
The comfyui Workflow is also embedded in this picture, you will have to install several custom extensions to make this work:
- Generator: Comfyui
- Positive Prompt: large format photo of (Masterpiece, best quality:1.2) A dancing ninja girl (wearing a wooden demon mask on the head:1.1) intricate ornamental carvings, medieval background, full body, cinematic lighting, Kodak Funsaver, Kodak Vision3, 50mm
- Negative Prompt: bad anatomy, bad proportions, blurry, cloned face, deformed, disfigured, duplicate, extra arms, extra fingers, extra limbs, extra legs, fused fingers, gross proportions, long neck, malformed limbs, missing arms, missing legs, mutated hands, mutation, mutilated, morbid, out of frame, poorly drawn hands, poorly drawn face, too many fingers, ugly, ugly, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, out of frame, ugly, extra limbs, bad anatomy, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, mutated hands, fused fingers, too many fingers, long neck
- Negative Embedding: FastNegativeV2
- Sampler: Euler
- Scheduler: normal
- CFG: 6
- Model: lyriel_v14
This is a quite interesting workflow as you can generate relatively long animations.
You draw the Motions of your character from a video. For this one i googled "dancing girl" and took one of the first i´ve found:
You can draw single images from the Video into comfyui. for this one i´ve skipped the first 500 Frames and took 150 Frames to generate the animation. The single images are scaled to the Resolution 512x512. This gives me a initial set of pictures to work with:
Via the openpose prepocessor you can get the Poses for every single image:
This can be fed to the openpose controlnet to get the correct pose for every single animation. Now we have following problem. We are all set with the Poses, but we also need a set of latent images which have to go trough the ksampler. The solution is to generate a single 512x512 latent image and blend it with every single VAE encoded Picture of the Video to get an empty latent image for every Frame:
We get a nice set of empty latents for the sampler:
then we let the ksampler together with the animate diff nodes and controlnet do its magic and we get a set of images for our animation ( The number of possible images seems to be limited by your system memory. i had no problem with 100, 150, 200, 250 images and have not tested higher numbers yet. I could not load the full video):
Last step is to put everthing together with the video combine node. You can set the frame rate here. 30 FPS seems to produce acceptable results.:
That's awesome work! You're getting better and better at this :)
It's too bad the embedding doesn't seem to work so well, maybe someone else has a solution for this?
I´ve tried to implement Loras in the Workflow and a face detailer to strengthen the lora effect. the Results are quite interesting (low quality comes from the webm format):
Gwen Tennyson Lora
Trump
Buscemi
The workflow is embedded in this picture ( The image is pre Face Detailer)
Its all a bit trial and error right now. this animation took about 20 Minutes on my machine. I would love to do some more tests with different models and embeddings or even loras but unfortunately my time for this is somewhat limited.
I love to do the contests to test new things out :-)
Visions for the future: If you could get a stable output for the background and the actors (maybe Loras?) you could "play out" your own scenes and transform them via stable diffusion to something great. thinking of epic fight scenes, or even short anmation films.
This whole stable diffusion thing is extremly interesting and in my opinion a game changer like the introduction of the mobile phone.
I'm glad you're enjoying the contests, your contributions are always welcome :)
Though you might want to consider making a post of your own, your work deserves a lot more exposure than just as a comment.
The idea of making your own consistent scenes sounds quite impressive, it's a bit out of my league though. Like you, I have limited time to invest in this hobby, I'll stick to my images :)
It's a while I haven't partaken in a community challenge, so here is my contribution, Glad to see how active it became.
Prompt A mysterious mask, lying on an altar, ritual knife, fantasy
Seed: 5823057, Dimensions: 512x512, Sampler: euler, Inference Steps: 75, Guidance Scale: 7.5, Model: dreamshaper_8, Negative Prompt: low quality,, Prompt Strength: 0
I haven't switched to XL as my PC is too old for that version, so good old dreamshaper does the trick
It's good to have you back, Ziggurat :)
Made with DALL-E 3 and ChatGPT 4.
Prompt:
Photorealistic image of a porcelain mask representing a barn owl. The porcelain is glazed with a rich shade of purple, giving it a lustrous finish. Instead of traditional feathers, the mask boasts meticulously cut amethyst gemstones, each resembling the form of a feather. These gemstone feathers glisten in varying shades of purple, harmonizing with the glazed porcelain. The mask's facial details are accentuated with golden gilding, and the eyes emit a mesmerizing gold glow, standing out against the purple backdrop.
I decided to make a matching robe, similar to what @ricecake@sh.itjust.works did with their matching armor.
Prompt:
Photorealistic image of a wizard's robe in a captivating lavender hue. The robe's velvet fabric glimmers subtly, reminiscent of enchanted porcelain. Its trim is uniquely adorned with amethyst gemstones meticulously cut to resemble delicate feathers, each glowing with a variety of lavender shades, suggesting a mystical origin. The robe is richly embroidered with golden threads, creating patterns of arcane symbols and ancient lore across its surface. It features dramatically wide sleeves and a high, pointed collar, elements that are emblematic of a wizard's dignified attire.
I really love that robe and wish it was real
Oh man, that robe is awesome! Fits the mask really well too. :)
| Clear Theme | +1 | |
|
| | Total | 1 points |
One of these days you're going to have to share your prompt. I am curious what you use to get these results (though part of me thinks it might be better not to know :)
;)
ultra advanced dyson corona mask Steps: 20, Sampler: DPM++ 3M SDE Karras, CFG scale: 7, Seed: 4095904850, Size: 768x1280, Model hash: 74dda471cc, Model: realvisxlV20_v20Bakedvae, Clip skip: 2, RNG: CPU, Version: v1.6.0
| Clear Theme | +1 | |
|
| | Prompt included | +1 | Total | 2 points |
Close second for originality! It really does look like a Dyson product, though I don't want to know where that hose is going :)
Bing prompt was "A highly detailed face pretending to be a spooky mask. San rio style, cgi"
I don't know if it's my connection, but your image isn't showing. The image URL doesn't seem to work either.
Edit: nevermind, it’s back again!
[a1111] detailed mask, dragon-like, cybernetic, dragon, electric, brushed aluminium, jade, gold filigree, hdr, (intricate details, hyperdetailed:1.6, hyperrealistic:1.4, symmetrical),cinematic shot,Masterpiece, high quality, best quality, maximum detail product render, beauty and aesthetics, BLTA android-seams, loraeyes vamptech Negative prompt: marker_(medium), faux_traditional_media, traditional_media, millipen_(medium),nib_pen_(medium), ballpoint_pen_(medium)_, (long neck:2), lowres, (cropped:1.6), ((shoulder , person, body, head)) BadDream UnrealisticDream bad_pictures Steps: 50, Sampler: DPM++ 2M Karras, CFG scale: 12.5, Seed: 949118021, Face restoration: GFPGAN, Size: 768x512, Model hash: eeeeb941cd, Model: theTalosProject_v11, Denoising strength: 0.2, Clip skip: 2, Hires upscale: 2, Hires steps: 12, Hires upscaler: 8x_NMKD-Superscale_150000_G, Lora hashes: "add_detail: 7c6bad76eb54, detail_slider_v4: 8347b7ec221e, epi_noiseoffset2: d1131f7207d6, BLTA2: 157e39f662bc, robot-seams: 06b804e8ab20, absolutereality_v181: f4f2d39f6b21, eddiemauroLora2: 73a91f50a4fe, Loraeyes_V1: da8286d2ab99, VampiricTech: 55dc9af60bfa", Version: v1.6.0
| Clear Theme | +1 | |
|
| | Prompt included | +1 | Total | 2 points |
Thank you for the mask! It's quite beautiful, I love the details in the gold and the glowing eyes.
Prompt: Mask, Raven, feather, blue, purple, black, feather mask, Luxury Traditional Venice Women Carnival Masquerade Venetian Mask, high quality, 4K, 8K
Negative Prompt: face, human, person
Style: Concept Art
Workflow(?): Web-based (Perchance.org)
I know it's originally meant for Midjourney, but would still like to share this link for those of us looking for some inspiration.
The many masks of Midjourney
My first go at an AI image was the other day on the Your username is the prompt post which was great fun....I've only got access to the free webpage generators so this is my effort
'vibrant tribal mask inspired by dinosaurs and adorned with feathers'
Done using Craiyon
Nice mask, and welcome to the community :)
Maybe it would be a good idea to have a post pinned with some information for those who want to get started with AI image generation.
AI Generated Images
Community for AI image generation. Any models are allowed. Creativity is valuable! It is recommended to post the model used for reference, but not a rule.
No explicit violence, gore, or nudity.
This is not a NSFW community although exceptions are sometimes made. Any NSFW posts must be marked as NSFW and may be removed at any moderator's discretion. Any suggestive imagery may be removed at any time.
Refer to https://lemmynsfw.com/ for any NSFW imagery.
No misconduct: Harassment, Abuse or assault, Bullying, Illegal activity, Discrimination, Racism, Trolling, Bigotry.
AI Generated Videos are allowed under the same rules. Photosensitivity warning required for any flashing videos.
To embed images type:
“![](put image url in here)”
Follow all sh.itjust.works rules.
Community Challenge Past Entries
Related communities:
- !auai@programming.dev
Useful general AI discussion - !aiphotography@lemmings.world
Photo-realistic AI images - !stable_diffusion_art@lemmy.dbzer0.com Stable Diffusion Art
- !share_anime_art@lemmy.dbzer0.com Stable Diffusion Anime Art
- !botart@lemmy.dbzer0.com AI art generated through bots
- !degenerate@lemmynsfw.com
NSFW weird and surreal images - !aigen@lemmynsfw.com
NSFW AI generated porn