Update README.md

README.md

@@ -25,26 +25,32 @@ pipeline_tag: text-to-image
 library_name: diffusers
 emoji: 🔜
 
-instance_prompt: MAYAK style Constructivist Poster
+instance_prompt: MAYAK style Constructivist Poster art
 
 widget:
+- text: MAYAK style drawing
+  output:
+    url: 1.jpg
+- text: MAYAK style
+  output:
+    url: 2.jpg
 - text: MAYAK style drawing of Osip Mandelshtam reciting /OH, BUT PETERSBURG! NO! IM NOT READY TO DIE! YOU STILL HOLD ALL THE TELEPHONE NUMBERS OF MINE!/
   output:
-    url: 1730641155080__000002800_3.jpg
+    url: 3.jpg
 - text: >-
     MAYAK style art of poet Mandelstam reading /YOU'VE RETURNED HERE, SO SWALLOW THEN, FAST AS YOU MIGHT, ALL THE FISH OIL OF LENINGRAD'S RIVERINE LIGHT!/
   output:
-    url: 1730641089182___1.jpg
+    url: 4.jpg
 
 ---
 <Gallery />
 
 # Mayakovsky Style Soviet Constructivist Posters & Cartoons Flux LoRA – Version 2 – by SOON®
-Trained via Ostris' [ai-toolkit](https://replicate.com/ostris/flux-dev-lora-trainer/train) on 50 high-resolution scans of 1910s/1920s posters & artworks by the great Soviet **poet, artist, & Marxist activist Vladimir Mayakovsky**.  <br> 
+Trained via Ostris' [ai-toolkit](https://github.com/ostris/ai-toolkit) on 50 high-resolution scans of 1910s/1920s posters & artworks by the great Soviet **poet, artist, & Marxist activist Vladimir Mayakovsky**.  <br> 
 For this training experiment, we first spent many days rigorously translating the textual elements (slogans, captions, titles, inset poems, speech fragments, etc), with form/signification/rhymes intact, throughout every image subsequently used for training.  <br> 
 These translated textographic elements were, furthermore, re-placed by us into their original visual contexts, using fonts matched up to the sources.  <br> 
 We then manually composed highly detailed paragraph-long captions, wherein we detailed both the graphic and the textual content of each piece, its layout, as well as the most intuitive/intended apprehension of each composition. <br> 
-Training went for 5000 steps at a DiT Learning Rate of .00001, batch 1, with the adafactor optimizer, and the text encoders trained alongside the DiT!<br> 
+This repo contains the 2400 step checkpoint and samples. Training went for 5000 steps at a DiT Learning Rate of .00001, batch 1, with the adafactor optimizer, and the text encoders trained alongside the DiT!<br> 
 No synthetic data was used for the training, nor any auto-generated captions! Everything was manually and attentively pre-curated with a deep respect for the sources used.  <br> 
 
 This is a **rank-64/alpha-64 Constructivist Art & Soviet Satirical Cartoon LoRA for Stable Diffusion 3.5 Large** <br>