Chinese Text To Image Generation Via Autoregressive Transformer Tokenization

via “text encoder and decoder with transformer-based generation”

Tiny vision-language model for edge devices.

Unique: Integrates vision-text cross-attention directly in the decoder, enabling grounded generation that references visual features at each decoding step vs separate vision and language modules

vs others: More efficient than LLM-based approaches (CLIP+GPT) for vision-grounded generation due to unified architecture, while maintaining flexibility through configurable generation parameters

via “cascaded transformer text-to-semantic-token conversion”

Open-source text-to-audio — speech, music, sound effects, 13+ languages, runs locally.

Unique: Uses a pure semantic token approach without phoneme intermediaries, enabling direct text-to-audio generation that preserves prosody and emotion in a single learned representation across 13+ languages

vs others: Avoids phoneme bottleneck of traditional TTS (Tacotron, Glow-TTS), enabling more natural prosody and cross-lingual expressiveness in a single model

via “next-token prediction with transformer decoder architecture”

text-generation model by undefined. 1,60,37,172 downloads.

Unique: Smallest publicly-released GPT model (124M parameters) with full architectural transparency and extensive fine-tuning examples, enabling researchers to study transformer behavior without computational barriers that gate access to larger models

vs others: Smaller and faster than GPT-3/3.5 for local deployment, but significantly less capable at reasoning, instruction-following, and factual accuracy — trades capability for accessibility and cost

via “image-to-text sequence generation with visual grounding”

image-to-text model by undefined. 83,58,592 downloads.

Unique: Implements cross-attention between visual patch embeddings and text token representations during decoding, allowing the model to dynamically reference image regions while generating text — unlike simpler CNN-to-RNN approaches that encode the entire image once

vs others: Provides better layout-aware extraction than CLIP-based approaches because it maintains visual grounding throughout decoding, while being more efficient than large multimodal models like GPT-4V due to smaller parameter count and local deployment

via “autoregressive text generation with transformer decoder architecture”

text-generation model by undefined. 79,12,032 downloads.

Unique: OPT uses a standard transformer decoder architecture with no architectural innovations, but distinguishes itself through permissive licensing (OPL) and transparent training methodology documented in arxiv:2205.01068, enabling reproducible research without commercial restrictions unlike GPT-3/4

vs others: Smaller and faster to run than GPT-2 (1.5B) with similar quality, but lacks instruction-tuning of Alpaca/Vicuna and safety alignment of InstructGPT, making it better for research baselines than production chatbots

via “auto-regressive text-to-image generation with discrete tokenization”

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

Unique: Implements discrete token-based generation (predicting from finite codebook) rather than continuous latent diffusion, enabling exact reproducibility and efficient caching of token predictions. Uses pluggable VAE implementations (OpenAI, VQGan, custom) allowing researchers to swap image encoders without retraining the transformer.

vs others: More interpretable and controllable than diffusion models due to discrete token representation, but slower generation speed; more memory-efficient than continuous latent approaches for long sequences due to finite vocabulary.

via “masked-token-prediction-for-chinese-text”

fill-mask model by undefined. 11,40,112 downloads.

Unique: Purpose-built for Chinese with a 21,128-token vocabulary optimized for Chinese character and subword distributions, trained on Chinese-specific corpora (Wikipedia, Baidu Baike) rather than multilingual data, enabling higher accuracy for Chinese masking tasks compared to multilingual BERT variants that dilute capacity across 100+ languages

vs others: Outperforms multilingual BERT on Chinese fill-mask tasks due to language-specific vocabulary and training data, while maintaining lower latency than larger models like RoBERTa-large-chinese due to 12-layer architecture

via “bitwise autoregressive image token prediction with infinite vocabulary scaling”

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

Unique: Replaces fixed-vocabulary token prediction with bitwise decomposition, enabling vocabulary scaling to 2^64 without discrete bottlenecks. Unlike diffusion models that denoise from noise, Infinity builds images token-by-token through sequential bit prediction, fundamentally different from both traditional autoregressive (GPT-style) and diffusion approaches.

vs others: Avoids vocabulary ceiling limitations of discrete-token autoregressive models and eliminates the iterative denoising steps of diffusion models, achieving competitive quality at 1024×1024 with a single forward pass per token.

via “chinese text-to-image generation via autoregressive transformer tokenization”

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

Unique: Unified autoregressive transformer architecture that treats text and images as discrete token sequences, enabling a single 4B-parameter model to handle generation, captioning, super-resolution, and reranking without task-specific heads. Uses VQ-VAE tokenization (8192 codes) to convert images to sequences, enabling transformer-based sequence prediction instead of pixel-space diffusion.

vs others: Simpler unified architecture than task-specific models, but slower inference than diffusion-based alternatives and limited to Chinese input in v1; stronger than concurrent autoregressive models (VQGAN-CLIP, DALL-E v1) in handling long-range dependencies via transformer attention.

via “dall·e bart decoder for image token sequence generation”

min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch

Unique: Implements autoregressive decoding with causal masking (each token only attends to previous tokens), enabling efficient single-pass generation of 256 tokens. Integrates supercondition_factor as a post-hoc mechanism to weight encoder output, avoiding the need for explicit classifier-free guidance training.

vs others: Simpler than non-autoregressive approaches (e.g., iterative refinement) while maintaining reasonable quality; faster than diffusion-based decoding (5-15s vs 30-60s) due to single-pass generation without iterative refinement steps.

via “language model decoding with image context integration”

image-to-text model by undefined. 1,67,827 downloads.

Unique: Integrates image tokens directly into the transformer decoder's attention mechanism rather than using a separate fusion layer, allowing the model to learn fine-grained associations between image patches and generated text tokens. Uses causal masking for text tokens while allowing full attention to image patches, enabling the model to reference visual content at any point during generation.

vs others: More efficient than encoder-decoder architectures with separate image and text encoders because it uses a unified transformer, but may sacrifice some caption quality compared to models with dedicated image understanding modules (e.g., BLIP-2 with ViT-L).

via “autoregressive-text-generation-from-visual-input”

image-to-text model by undefined. 1,64,795 downloads.

Unique: Implements cross-attention-based visual grounding in the decoder, allowing the model to dynamically focus on different image regions during text generation, rather than using static visual context — this enables better handling of spatially-distributed handwritten text and reduces hallucination of text not present in the image

vs others: More flexible than CTC-based OCR models (which require fixed output alignment) and more interpretable than end-to-end CNN-RNN approaches because attention weights reveal which image regions influenced each generated token

via “language-aware acoustic token prediction with transformer attention”

text-to-speech model by undefined. 1,57,348 downloads.

Unique: Applies transformer language modeling directly to acoustic token prediction (treating speech as discrete token sequence) rather than predicting continuous acoustic features — leverages Llama 3.2's pre-trained attention patterns and token prediction capabilities with minimal architectural modification

vs others: More efficient than continuous acoustic feature prediction (mel-spectrograms) due to discrete token compression; however, requires separate vocoder stage and may introduce quantization artifacts compared to end-to-end continuous prediction models like Glow-TTS or FastPitch

via “image-to-text generation via vision-language transformer (git model)”

* ⭐ 05/2022: [GIT: A Generative Image-to-text Transformer for Vision and Language (GIT)](https://arxiv.org/abs/2205.14100)

Unique: Uses a unified generative image-to-text transformer (GIT) that jointly processes visual features and text tokens in a single decoder, rather than separate vision and language components, enabling end-to-end training and more coherent image understanding through shared attention mechanisms

vs others: More efficient than two-stage approaches (object detection + description) by using end-to-end transformer architecture, and produces more natural descriptions than template-based captioning by leveraging large-scale pre-training

via “parallel multi-token prediction with non-autoregressive generation”

* ⭐ 02/2023: [Structure and Content-Guided Video Synthesis with Diffusion Models (Gen-1)](https://arxiv.org/abs/2302.03011)

Unique: Applies masked language modeling (from NLP) to image generation by predicting all image tokens in parallel rather than sequentially, enabling O(1) token prediction complexity per iteration instead of O(n) for autoregressive models

vs others: Achieves 5-10x faster generation than autoregressive pixel-space models (e.g., VQ-GAN-CLIP) because all tokens are predicted in a single forward pass, though requires multiple iterations to match quality

via “autoregressive text generation with 20b parameters”

* ⭐ 04/2022: [PaLM: Scaling Language Modeling with Pathways (PaLM)](https://arxiv.org/abs/2204.02311)

Unique: First open-source 20B-parameter model trained on diverse, curated data (EleutherAI's The Pile) with full architectural transparency and reproducible training pipeline, enabling community-driven optimization and fine-tuning without proprietary restrictions

vs others: Larger and more capable than GPT-2 (1.5B) with comparable inference cost to smaller models, while maintaining full open-source licensing unlike GPT-3 (closed API) and competitive with contemporaneous models like BLOOM-176B in capability-per-parameter efficiency

via “phonetic-aware text-to-speech token prediction”

* ⭐ 01/2023: [MusicLM: Generating Music From Text (MusicLM)](https://arxiv.org/abs/2301.11325)

Unique: Decomposes TTS into explicit phonetic token prediction followed by neural vocoding, rather than end-to-end waveform generation, allowing the language model component to focus purely on linguistic-to-acoustic mapping while the vocoder handles waveform reconstruction, enabling better generalization and interpretability

vs others: More linguistically interpretable than end-to-end models (tokens correspond to phonetic units) and more data-efficient than waveform-based approaches because the discrete token space is smaller and more structured than raw audio