ostris/ideogram_4_turbotime_lora - text-to-image
Hugging Face model: ostris/ideogram_4_turbotime_lora
#Image Generation
483 articles tagged with Image Generation
abgitdev/Typhoonminigen: Native macOS image generator for FLUX.2 Klein — fully on-device on Apple Silicon via MLX. No Python, no ComfyUI, no server.
Native macOS image generator for FLUX.2 Klein — fully on-device on Apple Silicon via MLX. No Python, no ComfyUI, no server.
boogu-project/Boogu-Image: Boogu-Image-0.1 is a competitive Apache-2.0 open-source image generation and editing model family, with Base, Turbo, and Edit variants supporting text-to-image, fast generation, image editing, and bilingual (Chinese/English) text rendering.
Boogu-Image-0.1 is a competitive Apache-2.0 open-source image generation and editing model family, with Base, Turbo, and Edit variants supporting text-to-image, fast generation, im...
【ディフューザーズがFLUX-2を歓迎】https://huggingface.co/blog/flux-2※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
【ディフューザーズがFLUX-2を歓迎】https://huggingface.co/blog/flux-2※AI生成の自動投稿（見出し＋リンク）#AI #生成AI #LLM #AIGenerated
Adobe Firefly wprowadza generator profesjonalnych portretów biznesowych, który wykorzystuje modele takie jak FLUX i Gemi...
Adobe Firefly wprowadza generator profesjonalnych portretów biznesowych, który wykorzystuje modele takie jak FLUX i Gemini do zamiany zwykłych zdjęć w studyjne headshoty. #si #ai #...
Ogni generazione sarà giudicata dalle risorse che avrà sprecato! Noi siamo ora in quella dell' #AI
Ogni generazione sarà giudicata dalle risorse che avrà sprecato! Noi siamo ora in quella dell' #AI
kukielp/cfml-image-with-cloudflare: Generate images from CFML by calling Cloudflare's Workers AI — text-to-image, image-to-image, inpainting, and model discovery — without writing a line of cfhttp yourself.
Generate images from CFML by calling Cloudflare's Workers AI — text-to-image, image-to-image, inpainting, and model discovery — without writing a line of cfhttp yourself.
prsunehria-lab/AI-Studio-Text-to-Image-Using-Stable-Diffusion-v1.5: A lightweight, fully offline Stable Diffusion v1.5 Web UI optimized for low-VRAM NVIDIA GPUs. Built with Flask, Diffusers, and Tailwind CSS. Features Txt2Img, Img2Img, interactive Inpainting Canvas, ControlNet (OpenPose & Recolor), and an automated MTCNN face-refining pipeline.
A lightweight, fully offline Stable Diffusion v1.5 Web UI optimized for low-VRAM NVIDIA GPUs. Built with Flask, Diffusers, and Tailwind CSS. Features Txt2Img, Img2Img, interactive ...
⚙️ La Cina resta un nodo per NVIDIA: tra restrizioni e mercato incerto, la risposta passa dalle CPU Vera, nuova scommess...
⚙️ La Cina resta un nodo per NVIDIA: tra restrizioni e mercato incerto, la risposta passa dalle CPU Vera, nuova scommessa per spingere l’AI oltre le GPU. #NVIDIA #AI🔗 https://www.t...
Flux raises USD $5 million to track AI code output
The new capital will help the Boston startup expand sales and engineering as firms seek clearer oversight of AI-assisted coding and software risk.
PlantPotatoOnMoon/HPSv3-PlusPlus: HPSv3++: Scaling Reward Models Across the Full Spectrum of Diffusion Model Capabilities
HPSv3++: Scaling Reward Models Across the Full Spectrum of Diffusion Model Capabilities
newideas99/open-dungeon: Open Dungeon — the first easy-to-use, fully local AI roleplay app. Story and inline scene images generated 100% on your machine (Gemma 4 QAT via Ollama(and others) + FLUX). No accounts, no API keys, no cloud.
Open Dungeon — the first easy-to-use, fully local AI roleplay app. Story and inline scene images generated 100% on your machine (Gemma 4 QAT via Ollama(and others) + FLUX). No acco...
Midjourney لا يكتفي بإنشاء صور فحسب—يهدف الآن إلى تحويل نصوصك إلى أفلام كاملين! 🎬 - **مفتاح التغيير**: تقنية “Text‑to‑Fi...
Midjourney لا يكتفي بإنشاء صور فحسب—يهدف الآن إلى تحويل نصوصك إلى أفلام كاملين! 🎬 - **مفتاح التغيير**: تقنية “Text‑to‑Film” تُنشئ مشاهد متسلسلة وفقًا لوصفك. - **ما يعنيه ذلك**: إبد...
Humans matter, AI still in flux and more lessons from Gartner summit
Key themes at the Application Innovation & Business Solutions Summit focused on the power of human ingenuity, common AI strategy mistakes, the rise of agentic AI and the need for g...
20+ image models, one place, $0, no sign up. The daily build is real. #FreeAI #AIart #Midjourney #FluxAI #aifreeforever ...
20+ image models, one place, $0, no sign up. The daily build is real. #FreeAI #AIart #Midjourney #FluxAI #aifreeforever #ai
Martin Scorsese has signed on as an adviser to Black Forest Labs, using their FLUX AI to generate storyboards. The Art D...
Martin Scorsese has signed on as an adviser to Black Forest Labs, using their FLUX AI to generate storyboards. The Art Directors Guild (IATSE Local 800) issued a formal statement c...
The same image models the big names charge $30/month for. Free here. #FreeAI #AIart #Midjourney #FluxAI #aifreeforever #...
The same image models the big names charge $30/month for. Free here. #FreeAI #AIart #Midjourney #FluxAI #aifreeforever #ai
Ücretsiz AI araçları arıyorsanız, doğru yerdesiniz! 🤖 ChatGPT, DALL-E ve daha fazlası ile yaratıcı projelerinizde sizi d...
Ücretsiz AI araçları arıyorsanız, doğru yerdesiniz! 🤖 ChatGPT, DALL-E ve daha fazlası ile yaratıcı projelerinizde sizi destekleyebilir. Hemen deneyin! #ChatGPT #LLM #AI #Teknoloji ...
wanshuiyin/ARIS-Movie-Director: Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.
Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelli...
20+ image models. One place. No login. #AIart #FreeAI #ImageGeneration #Midjourney #aifreeforever #ai
20+ image models. One place. No login. #AIart #FreeAI #ImageGeneration #Midjourney #aifreeforever #ai
i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
Diffusion models have consistently driven progress in text-to-image generation. However, it is challenging to attribute recent progress to specific modeling and data choices: state...
DyllonDunton1/Windmill_Diffusion_Tool: A Dockerized inference tool that fills missing wind turbine nacelle x/y motion in Excel files using a pretrained latent diffusion model, then calculates D10/d10 deflection metrics and generates motion, orbit, and deflection plots.
A Dockerized inference tool that fills missing wind turbine nacelle x/y motion in Excel files using a pretrained latent diffusion model, then calculates D10/d10 deflection metrics ...
Long time no post, very busy times. And although I would have dearly loved to talk about ecology, in the current flux of...
Long time no post, very busy times. And although I would have dearly loved to talk about ecology, in the current flux of news and articles I’m reading I feel obliged to make a post...