HologramHologram
ModelsIndex Nov 20, 2026

tessera-small

099

thejagstudio · 95.3 MB · CC BY-NC 4.0

Address
thejagstudio/tessera-small
Held on
Get it
Status
Verified
Base model
…
Lineage
…
Unchanged from base
…
Trending
#28
Downloads, 30 days
0
Weights
95.3 MB
Revision

Author: Jagrat Patel (TheJagStudio) Live demo: Tessera Pixel Studio License: CC BY-NC 4.0. Free for education, research and personal non-commercial use with credit.

At a glance

Task
Text to image
Input
text
Output
image
Library
pytorch
License
CC BY NC 4.0Non commercial
Released
Nov 2026
Updated
Nov 2026
Likes
12
Downloads, all time
0

Run it

Pinned to the indexed revision.

hf download thejagstudio/tessera-small --revision e019edd7b29367821c05e6261bc40294ce6f8d27

Through the hub: the same tools, each file from a source that is up (Hugging Face, ModelScope, IPFS), at this revision. The last line checks every file against the hash the tree names.

export HF_ENDPOINT=https://gethologram.ai
hf download thejagstudio/tessera-small --quiet && hf cache verify thejagstudio/tessera-small

Datasets

Spaces

Used in 2 Spaces.

Read the full model card

Tessera-small: a diffusion language model for 16×16 pixel art

Author: Jagrat Patel (TheJagStudio) Live demo: Tessera Pixel Studio License: CC BY-NC 4.0. Free for education, research and personal non-commercial use with credit. Commercial use is not allowed without a separate license from the author.

showcase

Tessera treats a 16×16 sprite as a 256-token sentence. Every pixel is one token from a learned 512-color palette (token 0 = transparent). A bidirectional transformer starts from a fully masked canvas and unmasks all 256 pixels in parallel in about 16 steps, conditioned on a frozen CLIP text encoder. It has no VAE, no latent space and no autoregression.

Model

Parameters 47.6M (Tessera-small)
Architecture joint text+pixel bidirectional transformer, hourglass 2 + 8 + 2 blocks (2×2 patch-merged core), width 512, 8 heads, QK-RMSNorm, 2D axial RoPE, Conv-SwiGLU, adaLN-single, 4 registers, self-conditioning
Text encoder frozen openai/clip-vit-base-patch32 text tower, 24 tokens (not included, MIT licensed)
Vocabulary 512 palette tokens (frequency-weighted OKLab k-means, ΔE 0.010) + [MASK]
Objective absorbing-state masked diffusion, cosine schedule, blob masks, perceptual label smoothing, CFG dropout
Sampler parallel confidence-ordered unmasking with CFG, Gumbel-annealed choice, spatial NMS; inpainting supported

Training

82,342 steps × 512 sprites (30 epochs over 1.4M sprites) on one NVIDIA RTX PRO 6000 Blackwell (≈5.5 h). The optimizer is Muon for hidden matrices plus AdamW, with a Warmup-Stable-Decay schedule, EMA 0.9995, bf16 and torch.compile.

Metric (EMA weights) Value
Validation NLL 0.859 nats / pixel (perplexity 2.36 of 512)
Validation accuracy 78.8% of masked pixels
CLIP score (ViT-B/32) 25.24 generated vs 25.28 real sprites

Usage (non-commercial)

from huggingface_hub import hf_hub_download
from tessera.pipeline import TesseraPipeline   # code: see the demo Space's files

ckpt = hf_hub_download("thejagstudio/tessera-small", "tessera-small-fp16.pt")
pipe = TesseraPipeline.from_checkpoint(ckpt, device="cuda")
images = pipe(["golden crown with blue gems"], num_per_prompt=8, steps=16, cfg_scale=3.0, seed=0)
pipe.grid(images).save("crowns.png")

Files

File Contents
tessera-small-fp16.pt EMA weights (fp16), model config, palette, text-encoder id, training step
model_config.json, train_config.json architecture and training hyperparameters
metrics.jsonl full training and validation log
showcase.png sample grid (16 prompts × 8 samples)

Credits

Huge thanks to Angais for creating and openly releasing Pixel Art Atlas 1.4M. This model was trained on it and would not exist without it.

License

Tessera is released under Creative Commons Attribution-NonCommercial 4.0.

  • ✅ Allowed (free): education, teaching, academic and independent research, personal projects and experiments. You can download, run, fine-tune and share the model, with credit ("Tessera by Jagrat Patel (TheJagStudio)").
  • ❌ Not allowed: any commercial use of the model or of images generated with it, such as selling or licensing it, paid apps, games or products, or monetized hosted services.
  • 💼 Commercial license: contact Jagrat Patel via Hugging Face.

Third-party parts keep their own licenses: the CLIP text encoder (OpenAI, MIT) and the Pixel Art Atlas 1.4M dataset (Angais).

© 2026 Jagrat Patel (TheJagStudio).

Derived on Nov 17, 2026 from Hugging Face at revision e019edd7, README.md .