Downloads · 30 days
49
20% of all-time downloads
AlekseyCalvin/Mayakovsky_Posters_SD3.5-L_3Ksteps_rank64_adafactor
Mayakovsky_Posters_SD3.5-L_3Ksteps_rank64_adafactor is a text-to-image model from AlekseyCalvin. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
Downloads · 30 days
49
20% of all-time downloads
All-time downloads
240
Public
Repo size
651 MB
Likes
1
Public
Click a slice to open those files.
.safetensors651 MB · 100%
From the Hugging Face model README
Trained via 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> This is the LoRA checkpoint at step 3000, trained at a DiT Learning Rate of .00001, batch 1, with the adafactor optimizer, and the text encoders trained alongside the DiT. The results are, unfortunately, messier and not as convergent as we'd hoped, even compared to the Flux versions (trained on the same data-set and available here as well). Tactical prompting may perhaps mediate this somewhat. And at least when and where S.D.3.5 breaks during training, it does so in wildly creative and often surprising ways, which sometimes even befit certain art styles. <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>
Check out our translations of Mayakovsky's verse-works, adapted from a proto-Soviet song-tongue into a Worldish one...<br> And found, along with many other poets' songs and tomes... Over at SilverAgePoets.com!
You should use MAYAK style or MAYAK style Constructivist poster art or MAYAK style satyrical drawing or suchlike to summon the poet's deathlessly pens and brushes.
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers