PromptCraft AI: Free Prompt Generator for Midjourney, DALL-E 3 & Stable Diffusion
If you use Midjourney, DALL-E 3, Stable Diffusion, or Flux, you know the struggle: writing the...
#Image Generation
391 articles tagged with Image Generation
Dev-next-gen/flux-amd-rocm: FLUX.1-dev on AMD Radeon consumer GPUs — fast, low-VRAM, and shippable. Backport patches + benchmarks for torchao + diffusers group_offload on ROCm.
FLUX.1-dev on AMD Radeon consumer GPUs — fast, low-VRAM, and shippable. Backport patches + benchmarks for torchao + diffusers group_offload on ROCm.
The Flux AI News: Latest AI Tools and Updates
Stay updated with the latest AI tools, ChatGPT news, OpenAI updates, creator tools, automation software, and trending AI ...
VISION-SJTU/SSG: [CVPR 2026 Oral] Guiding a Diffusion Model by Swapping Its Tokens
[CVPR 2026 Oral] Guiding a Diffusion Model by Swapping Its Tokens
わたしがペンギンの亜人ではないように、日本も日本ではないのかもしれませんHDモードの速度が3倍、コストが1/3になった「Midjourney」v8.1 Alphaが利用可能に ほか【ダイジェストニュース】 https://forest.wa...
わたしがペンギンの亜人ではないように、日本も日本ではないのかもしれませんHDモードの速度が3倍、コストが1/3になった「Midjourney」v8.1 Alphaが利用可能に ほか【ダイジェストニュース】 https://forest.watch.impress.co.jp/docs/digest/2101975.html#Apple #LLM #news ...
Shuyun-Wang/M-GDM: [CVPR'25] The official implementation of paper "Blind Bitstream-corrupted Video Recovery via Metadata-guided Diffusion Model"
[CVPR'25] The official implementation of paper "Blind Bitstream-corrupted Video Recovery via Metadata-guided Diffusion Model"
MicrosoftのBing検索に無料の動画生成AI「Sora」が実装/画像生成・編集AIモデル「FLUX.1 Kontextシリーズ」【今週公開の最新AIツール&ニュース】https://www.aiandemily.com/micros...
MicrosoftのBing検索に無料の動画生成AI「Sora」が実装/画像生成・編集AIモデル「FLUX.1 Kontextシリーズ」【今週公開の最新AIツール&ニュース】https://www.aiandemily.com/microsoft%e3%81%aebing%e6%a4%9c%e7%b4%a2%e3%81%ab%e7%84%a1%e6%96%9...
ABM4ALL/melodie-skills-example: An EV diffusion model created as an example of `melodie-skills`, in less than 1 hour, without a single line of code touched, pass@1.
An EV diffusion model created as an example of `melodie-skills`, in less than 1 hour, without a single line of code touched, pass@1.
unsloth/ERNIE-Image-Turbo-GGUF - text-to-image
Hugging Face model: unsloth/ERNIE-Image-Turbo-GGUF
💎30 ready-to-use prompts ✅Easy Use ⭐Create stunning stone mascots with this Midjourney master-prompt. Perfect for Etsy c...
💎30 ready-to-use prompts ✅Easy Use ⭐Create stunning stone mascots with this Midjourney master-prompt. Perfect for Etsy clipart, junk journals, stickers, and greeting cards. Isolate...
baojudezeze/Qwen-dpo: Training code for Diffusion-DPO applied to the Qwen Image-2512 model. This implementation builds on the training framework provided by zk1009 and follows the methodology described in the paper “Diffusion Model Alignment Using Direct Preference Optimization”.
Training code for Diffusion-DPO applied to the Qwen Image-2512 model. This implementation builds on the training framework provided by zk1009 and follows the methodology described ...
Butter-Crab/StructDiff: Official pytorch implementation of the paper: " StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation"
Official pytorch implementation of the paper: " StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation"
baidu/ERNIE-Image: ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu. It is built on a single-stream Diffusion Transformer (DiT), with only 8B DiT parameters, it reaches state-of-the-art performance among open-weight text-to-image models.
ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu. It is built on a single-stream Diffusion Transformer (DiT), with only 8B DiT param...
À l’ISE 2026, #Flux:: dévoile les nouvelles versions de #SPAT #Revolution et #MIRA. Gaël Martinet revient longuement sur...
À l’ISE 2026, #Flux:: dévoile les nouvelles versions de #SPAT #Revolution et #MIRA. Gaël Martinet revient longuement sur l’innovation immersive, l’intégration chez #Harman et une v...
Midjourney V7 in 2026: What Actually Changed for Builders?
I spent time revisiting Midjourney V7 from a builder's point of view, and the conclusion is more...
ミッドジャーニー完全ガイド【たった1動画で理解出来るMidjourneyの教科書】初心者OK！https://www.aiandemily.com/%e3%83%9f%e3%83%83%e3%83%89%e3%82%b8%e3%83%a3%...
ミッドジャーニー完全ガイド【たった1動画で理解出来るMidjourneyの教科書】初心者OK！https://www.aiandemily.com/%e3%83%9f%e3%83%83%e3%83%89%e3%82%b8%e3%83%a3%e3%83%bc%e3%83%8b%e3%83%bc%e5%ae%8c%e5%85%a8%e3%82%ac%e3%82%...
Rethinking the Diffusion Model from a Langevin Perspective
Diffusion models are often introduced from multiple perspectives, such as VAEs, score matching, or flow matching, accompanied by dense and technically demanding mathematics that ca...
SairajNarayankar/text-to-image-generation-pipeline: 🎨 Text-to-Image Generation Pipeline ✨ Production-Grade Generative AI System Advanced Text-to-Image generation using Stable Diffusion with 14 style presets, latent space operations, and enterprise-ready deployment.
🎨 Text-to-Image Generation Pipeline ✨ Production-Grade Generative AI System Advanced Text-to-Image generation using Stable Diffusion with 14 style presets, latent space operations,...
How I Built an AI Birthday Photo Generator with Cloudflare Workers, Gemini 2.5 Flash, and FLUX.2 Pro
TL;DR: Upload a selfie → Gemini analyzes the photo and writes 3 birthday scene prompts → FLUX.2 Pro...
EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model
We propose EditCrafter, a high-resolution image editing method that operates without tuning, leveraging pretrained text-to-image (T2I) diffusion models to process images at resolut...
i cancelled ChatGPT, Midjourney, and Copilot. here's the $0/month stack that replaced all three.
ChatGPT Plus: $20/month. Midjourney: $10/month. GitHub Copilot: $10/month. That's $480/year for AI...
rlgnswk/Preserve-and-Personalize: Official repository for "Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift" (ICLR2026)
Official repository for "Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift" (ICLR2026)
画像生成AI「FLUX.2」のデコード処理を1.4倍高速化する「FLUX.2 Small Decoder」が登場 https://web.brid.gy/r/https://gigazine.net/news/20260409-flux-2...
画像生成AI「FLUX.2」のデコード処理を1.4倍高速化する「FLUX.2 Small Decoder」が登場 https://web.brid.gy/r/https://gigazine.net/news/20260409-flux-2-small-decoder/
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping
In this paper, we introduce MegaStyle, a novel and scalable data curation pipeline that constructs an intra-style consistent, inter-style diverse and high-quality style dataset. We...