As soon as the model was trained, the first step was randomly generating a large set of images w. a simple prompt ("golem, detailed, realistic, 3D rendering")
Each golem can be extracted by removing the images' backgrounds (reco: @photoroom_app).
Some of the designs are amazing. However, the golems all look very similar to each other. Let's separate them into categories.
The following step is to prompt some more precise description (e.g. "golem with stone, lava, steel, fire")
Here's a first set of 16 golems that look consistent.
Because that initial set of lava golems was a bit simplistic, I used #img2img and an improved prompt to slightly increase the level of details (e.g. "3D rendering, trending on Artstation, etc.)
Here's the result:
And now, we can keep the same prompt and introduce many other variations while keeping the overall shape, posture, and level of detail.
Here are the ice golems (like the ones in Clash of Clans)
The forest golems! My favorites 🌲🌳
The sand golems 🏜️
And... the golden golem (directly inspired by the golden golem in Minecraft, via #img2img)
Now it's also possible to use the same finetune, and generate pictures that could be used elsewhere than in the game (ads, splash screens, etc).
Just add "Greg Rutkowski" in the prompt and start seing some cinematic composition, dramatic lighting, etc.
Some other tests I made...
As always, feel free to add any questions, feeback, remarks (and don't forget to like/follow/RT if you find this content interesting. I really appreciate it!)
Tomorrow, I'll keep sharing other explorations with #StableDiffusion 🚀🚀
(11/06 update - here's another run to create more characters, this time with "Space Marines" heavy infantry)
From multiple consistent objects within a single image to fully recreated 3D objects in Blender.
100% AI-generated.
Workflow detailed below 👇
Step 1/
Generate a grid of 6 consistent objects. For this, I used @Scenario_gg with the "Juicy Icons" model, which consistently creates cartoon-style, simplified 3D icons arranged in a grid.
Absolutely loving that this is happening during GDC week 😅. My schedule's packed with meetings & meetups, so not much time to vibe code, but I spun up a basic demo for a platformer jumping game, in minutes.
This was fully prompted via Claude 3.7 (on the left), zero manual tweaks. Link below 👇 and I'll keep sharing improvements and tips!
2025 is going to be a wild year for AI-powered game devs.
I used @JustinPBarnett's MCP on Github - check it out here
So far, it feels even easier than Blender, and I can’t wait to add more actions, assets, textures, and gameplay!github.com/justinpbarnett…
My main tip so far is that, just like with Blender MCP, you should proceed step by step >> one edit or element at a time.
Otherwise, Claude will go crazy and wil try doing everything at once (and fail).
Here are the key steps to creating stunning turnaround, using #Scenario ()
1/ Train or pick a character model (A).
2/ Optionaly>, pick a style model (B). Use it to create training images for (A), or you can merge both (A + B = C) for example.
3/ Utilize the custom model (A or C) to generate consistent characters. Then select a reference image to produce initial character turnarounds in your desired poses.
4/ Refine these initial outputs using Sketching and image2image.
5/ Select the best result and refine details in the Canvas for maximum consistency.
6/ Finally, upscale your final image (up to 8K resolution.)