Add image-blast-character skill: auto-rigged humanoid characters from one image#4
Open
gnoblin wants to merge 1 commit into
Open
Add image-blast-character skill: auto-rigged humanoid characters from one image#4gnoblin wants to merge 1 commit into
gnoblin wants to merge 1 commit into
Conversation
…mage A new skill that turns one reference image (or text prompt) into a rigged, animated humanoid GLB ready for any game engine. Wraps the existing `meshy-3d.mjs` script with the rigging + animation flags already in the repo as a first-class skill, alongside `image-blast-3d` (static props) and `image-blast-world` (Marble environments). Why this is its own skill rather than an `image-blast-3d` flag: - Inputs are pose-sensitive — Meshy auto-rig only works on humanoids in a T-pose / A-pose, front view, clean background. The skill scaffolds a flux-schnell prompt that produces that shape reliably, instead of expecting users to know the requirements. - Output is multi-clip (walking.glb + running.glb + rigged_character.glb) and the skill spells out which file to import for which use case. - Fallback path is non-obvious: non-humanoid input → fall back to `image-blast-3d` (static) and tell the user to rig manually in Blender or via an external tool. The skill documents this so it isn't a silent failure. End-to-end tested on two characters — a zombie and a skeleton warrior — generated with the same prompt scaffold, both auto-rigged and animated in ~4 minutes wall clock at ~$1 each in FAL credits. Demo / showcase repo using this skill plus the rest of the image-blaster pipeline: https://github.com/aignoblin/image-blaster-unity Agent: claude-mac Session: 1d0f99f7-68e3-4c8a-b96a-18b25cd92e10 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hey @neilsonnn — a new skill that pairs with the existing
image-blast-3d/image-blast-world/ etc.What it does
Takes a text prompt or a T-pose reference photo, returns a rigged + animated humanoid GLB. Wraps the
meshy-3d.mjsscript that's already in the repo (as a--provider meshyoption toimage-blast-3d) into a dedicated skill so character workflows have first-class instructions.Why a separate skill, not a flag on
image-blast-3dwalking.glb+running.glb+rigged_character.glbseparately. The skill documents which file to use for which engine state.image-blast-3dstatic + note user should rig manually.Tested
Same prompt scaffold, two completely different characters (zombie + skeleton warrior), both auto-rigged successfully, ~4 min, ~$1 each. Screenshots in downstream demo: https://github.com/aignoblin/image-blaster-unity
Diff
One file:
.claude/skills/image-blast-character/SKILL.md, 124 lines, same frontmatter convention as existing skills. No new deps. Purely additive.Thanks for
image-blaster🙏