#Image Generation

GitHub Trending repo Aug 20

Terminator1321/TTI-Diffusion: A text-to-image diffusion model built from scratch in PyTorch — trained on the Stanford Cars dataset with BLIP captions. Includes a custom BPE text tokenizer/encoder, a conditional U-Net denoiser, a cosine noise schedule, and a separate super-resolution upscaler that takes the 64×64 diffusion output up to 256×256.

A text-to-image diffusion model built from scratch in PyTorch — trained on the Stanford Cars dataset with BLIP captions. Includes a custom BPE text tokenizer/encoder, a conditional...

Image Generation

32

GitHub Trending repo Aug 19

sadpudding/stable-diffusion-pro-ui-2026: Optimized Stable Diffusion WebUI setup with SDXL, Flux, and ControlNet pre-installed. Includes 20 top models and LoRAs ready to use on first launch.

Optimized Stable Diffusion WebUI setup with SDXL, Flux, and ControlNet pre-installed. Includes 20 top models and LoRAs ready to use on first launch.

Stability AI Image Generation

50

GitHub Trending repo Aug 19

xuxun-oss/dsh-vision-imagen: DeepSeek Harness all-in-one: no model switching — regular DeepSeek auto-routes to vision & image gen. Multi-backend: Gemini + any OpenAI-compatible (GPT-4o, Qwen-VL, GLM-4V, gpt-image, DALL-E, Flux, OpenRouter). gemini_vision/gemini_generate_image/gemini_optimize_image with vision self-check. Better than modlens.

DeepSeek Harness all-in-one: no model switching — regular DeepSeek auto-routes to vision & image gen. Multi-backend: Gemini + any OpenAI-compatible (GPT-4o, Qwen-VL, GLM-4V, gpt-im...

OpenAI Google Image Generation

35

Mastodon discussion Aug 19

A guide to Flux.2-Klein-9B-MatchingPose covering setup, prompting, use cases, limitations, inference settings, and compe...

A guide to Flux.2-Klein-9B-MatchingPose covering setup, prompting, use cases, limitations, inference settings, and competing LoRAs. https://hackernoon.com/flux2-klein-9b-matchingpo...

Image Generation

9

Mastodon discussion Aug 18

AI models get convenient amnesia about source material as they grow, MIT boffins findAttributing diffusion model output ...

AI models get convenient amnesia about source material as they grow, MIT boffins findAttributing diffusion model output to a specific input becomes more difficult with more trainin...

Google Image Generation

18

GitHub Trending repo Aug 18

siddhantbhattarai/metacleaner: A local, offline metadata cleaner and AI-tag remover for images, text/Markdown, HTML, and Office documents, written in Rust. Strips EXIF, GPS, XMP, IPTC, C2PA, and AI-generator signatures (Stable Diffusion, DALL-E, Midjourney, Firefly), invisible-Unicode steganography, and document metadata. No network calls, no upload. Install via apt.

A local, offline metadata cleaner and AI-tag remover for images, text/Markdown, HTML, and Office documents, written in Rust. Strips EXIF, GPS, XMP, IPTC, C2PA, and AI-generator sig...

OpenAI Stability AI Image Generation

35

GitHub Trending repo Aug 17

r-vage/ComfyUI_SmartModelLoader: Secure diffusion model loaders and verified CivitAI/Hugging Face Download Manager for ComfyUI.

Secure diffusion model loaders and verified CivitAI/Hugging Face Download Manager for ComfyUI.

Hugging Face Image Generation

35

Papers with Code paper Aug 17

An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models

This paper investigates an increasingly important topic in generative modeling: pixel-space diffusion models. Although numerous studies have explored this topic, most focus on smal...

Image Generation

21

Papers with Code paper Aug 17

DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization

As text-to-image generative models advance, they raise critical safety concerns, particularly the generation of Not-Safe-For-Work (NSFW) content such as violence and nudity, furthe...

Image Generation

21

NewsData.io news Aug 15

Cringebot3000 Exposes LinkedIn’s AI Slop Trap: One Experiment, Sky-High Reach, And A Platform In Flux

Katie Notopoulos tested Cringebot3000 and watched her cheesy AI-generated LinkedIn post outperform typical content with massive stranger reach. The experiment reveals why low-quali...

Image Generation

21

GitHub Trending repo Aug 15

dickpy/dsh-imagegen: DSH (DeepSeek Harness) Web GUI AI image generation plugin: text-to-image & image-to-image via OpenAI-compatible endpoints (gpt-image-2), with shared cross-device history.

DSH (DeepSeek Harness) Web GUI AI image generation plugin: text-to-image & image-to-image via OpenAI-compatible endpoints (gpt-image-2), with shared cross-device history.

OpenAI Image Generation

35

GitHub Trending repo Aug 15

DjDevilCloud/EmitterRefusion: Novel Text To Image Architecture

Novel Text To Image Architecture

Image Generation

32

GitHub Trending repo Aug 15

xiaozhe7772222/dsh-draw-router: Universal image generation router for DeepSeek Harness (DSH): auto-discovers image models from any OpenAI-compatible endpoint. Supports SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more. | DeepSeek Harness 统一绘图路由器

Universal image generation router for DeepSeek Harness (DSH): auto-discovers image models from any OpenAI-compatible endpoint. Supports SenseNova, StepFun, Agnes, Qwen, Flux, SD, I...

OpenAI Image Generation API

35

GitHub Trending repo Aug 15

mbsdeepak/text-diffusion-fashion-mnist: Text-conditioned diffusion model (tiny Stable Diffusion) built from scratch in PyTorch, trained on Fashion-MNIST — CLIP text conditioning, DDIM sampling, classifier-free guidance.

Text-conditioned diffusion model (tiny Stable Diffusion) built from scratch in PyTorch, trained on Fashion-MNIST — CLIP text conditioning, DDIM sampling, classifier-free guidance.

Stability AI Image Generation

35

Mastodon discussion Aug 14

ComfyUI - The most powerful and modular diffusion model GUI, Run image/video generation models locally with easehttps://...

ComfyUI - The most powerful and modular diffusion model GUI, Run image/video generation models locally with easehttps://github.com/comfy-org/comfyui#comfyui #foss #opensource #gith...

Image Generation

18

GitHub Trending repo Aug 13

htoklu/HalimLabs3: Halim Labs 3 is a Windows image studio for NVIDIA Build: text-to-image, attach photos, and clothing try-on. Get a free nvapi key from build.nvidia.com (Get API Key) and paste it in Settings. API keys are not in this repository. Portable single EXE, no installer. Includes full .NET 8 WPF source code. Dark UI. Turkish prompts. Uses FLUX AI.

Halim Labs 3 is a Windows image studio for NVIDIA Build: text-to-image, attach photos, and clothing try-on. Get a free nvapi key from build.nvidia.com (Get API Key) and paste it in...

NVIDIA Image Generation API

35

GitHub Trending repo Aug 13

whp199/GemmaPrompt: Local prompt enhancer for ComfyUI diffusion models, with Gemma-chan as your (extremely reluctant) prompt supervisor. Writes in each model's native dialect — booru tags for Anima, prose for FLUX.2 Klein and Krea 2, MiniMax H3's structured rewrite. Any OpenAI-compatible LLM backend.

Local prompt enhancer for ComfyUI diffusion models, with Gemma-chan as your (extremely reluctant) prompt supervisor. Writes in each model's native dialect — booru tags for Anima, p...

OpenAI Google LLM

38

Mastodon discussion Aug 12

🎨 Where open-source stands in image editing:#16 FLUX.2 [max] — the best model you can actually download59 ELO points beh...

🎨 Where open-source stands in image editing:#16 FLUX.2 [max] — the best model you can actually download59 ELO points behind Reve 2.1 (Reve)Blind human preference, not marketing →ht...

Image Generation Open Source

9

GitHub Trending repo Aug 12

MansiiSapariya/flickr8k-text-to-image-lora: LoRA fine-tuning of Stable Diffusion v1.5 on Flickr8k for text-to-image generation with a Gradio inference interface.

LoRA fine-tuning of Stable Diffusion v1.5 on Flickr8k for text-to-image generation with a Gradio inference interface.

Stability AI Image Generation Fine-Tuning

32

Hugging Face model Aug 12

Gazingstars123/Anima-2.9B - text-to-image

Hugging Face model: Gazingstars123/Anima-2.9B

Image Generation

21

Mastodon discussion Aug 12

Explore FLUX.2-dev-Fun-Controlnet-Union, its pose, depth, edge, scribble and grayscale controls, setup, limitations and ...

Explore FLUX.2-dev-Fun-Controlnet-Union, its pose, depth, edge, scribble and grayscale controls, setup, limitations and 2602 improvements. https://hackernoon.com/a-guide-to-flux2-d...

Image Generation

9

Dev.to tutorial Aug 12

My Node.js Text-to-Image Gate: A Web App API Contract Test

Pick the text-to-image API that makes its response contract easy to test, then hide that contract...

Image Generation API

12

Mastodon discussion Aug 11

🔥 Still using the same AI image generator for everything?ChatGPT, Gemini, Midjourney, FLUX, Ideogram, Recraft, Firefly &...

🔥 Still using the same AI image generator for everything?ChatGPT, Gemini, Midjourney, FLUX, Ideogram, Recraft, Firefly & Runway all have different strengths.I compared 8 of the bes...

OpenAI Google Image Generation

9

GitHub Trending repo Aug 10

ken978451-boop/text-to-image-studio: A small, secure OpenAI Image API example that turns text prompts into images.

A small, secure OpenAI Image API example that turns text prompts into images.

OpenAI Image Generation API

35