Add LoRA space builder skill#152
Merged
evalstate merged 8 commits intoJun 8, 2026
Merged
Conversation
apolinario
approved these changes
Jun 4, 2026
# Conflicts: # .claude-plugin/marketplace.json # .claude-plugin/plugin.json # .cursor-plugin/marketplace.json # .cursor-plugin/plugin.json # gemini-extension.json
…r-skill # Conflicts: # gemini-extension.json
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds
huggingface-lora-space-builder: builds and publishes a Gradio Space on Hugging Face for a user-provided LoRA (discussed here as well).HF_TOKEN/huggingface-cli loginsessionand only prompts for a token when the cached one can't read the LoRA.
HfApi+ModelCardto infer the base model, pick the right.safetensors(READMEhint →
pytorch_lora_weights.safetensors→ latest checkpoint → ask), and surface trigger words,recommended steps, guidance scale, and LoRA scale.
diffusersinference recipe per base model (Qwen-Image, Qwen-Image-Edit,LTX-Video, Wan, FLUX, SDXL, …) and designs a UI tailored to the LoRA's task and inputs.
@spaces.GPU(duration=...)to thetask, and reaches for
size="xlarge"only whenlargeOOMs.HF_TOKENas a Space secret when the LoRA or base model is private/gated.back to CPU but points the user at a PRO upgrade or a community GPU grant.
Co-authored with Claude Code & @apolinario