LeafCat79 commited on
Commit
311fb99
·
verified ·
1 Parent(s): 567019b

Document image generation options

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -13,4 +13,6 @@ pinned: false
13
 
14
  Paste an HTML game, describe asset roles like `player`, `background`, or `enemy`, and generate a rewritten version of the game with image data embedded directly into the HTML.
15
 
16
- The app generates images with Pollinations/FLUX-style image URLs, converts the results into base64 data URIs, replaces matching asset filenames in the provided HTML, and previews the result in a sandboxed iframe.
 
 
 
13
 
14
  Paste an HTML game, describe asset roles like `player`, `background`, or `enemy`, and generate a rewritten version of the game with image data embedded directly into the HTML.
15
 
16
+ The app interprets the shared art style into explicit per-role image prompts, then generates and embeds game assets as base64 data URIs.
17
+
18
+ If the Space has an `HF_TOKEN` secret, it will try the Hugging Face image model in `HF_IMAGE_MODEL` first. The default model is `black-forest-labs/FLUX.1-schnell`. Without that secret, the app uses a local style-aware Pillow fallback that varies watercolor, vector/neon, claymation, oil-painting, anime, and pixel-art looks.