Post5/13/2026, 11:01:43 PM@cocktailpeanutposted inHiDream O1 Image FP8HiDream O1 Full FP8 Support0 commentsJust added support for FP8-FULL (previously only FP8-Dev was supported!) Commit: https://github.com/cocktailpeanut/hidr…
Post5/10/2026, 3:47:01 PM@cocktailpeanutposted inHiDream O1 Image FP8Run HiDream-o1-image with Low VRAM (10GB)0 commentsThis launcher lets you run the official web ui from the HiDream-o1-image project at https://github.com/HiDream-ai/HiDre…
Post5/10/2026, 3:38:28 PM@cocktailpeanutposted inHiDream-O1-ImageHiDream-O1-Image: a single transformer image generation model with reasoning skills0 commentsWhat is architecturally novel? HiDream-O1-Image is a single transformer that works directly on raw pixels. - no VAE - n…
Check-in5/10/2026, 3:12:23 PM@cocktailpeanutchecked in toHiDream O1 Image FP8sha256:81590677...2ac9cd2c•2 check-insConfirmed on win32 · x64 · nvidia rtx a4500win32x64GPU: nvidia rtx a4500RAM: 28 GBVRAM: 19 GBCommit messages (2)cocktailpeanut/hidream-o1—Add webui_enhancements.js, Update 3 files0c77121pinokio · 5/10/2026hidream-ai/hidream-o1-image(app)—add gradio5dd7616Qi Cai · 5/9/2026Last by @itouch44•5/10/2026, 10:25:21 PM
Post5/9/2026, 7:07:47 PM@cocktailpeanutposted inds4-webuids4.c reasoning in action -- reasons better than me!0 commentsI tried some interesting questions to test the reasoning capabilities of deepseek4 (powered by ds4 ). Here's one image …
Post5/9/2026, 5:13:13 PM@cocktailpeanutposted inds4-webuids4-webui: DeepSeek v4 Web UI for Apple Devices with 128GB+ memory0 commentsds4-webui is a web ui for running DeepSeek V4 Flash locally through ds4.c From a user's point of view, it gives you a o…
Post5/9/2026, 4:31:33 AM@cocktailpeanutposted inOverworldOverworld Low VRAM Word Model Simulator0 commentsBelated post on Overworld launcher--This app runs the Overworld Biome server, on NVIDIA GPU machines with at 8GB VRAM. …
Post5/8/2026, 4:23:48 AM@cocktailpeanutposted inds4[Research] ds4 Models and System Requirements0 comments#llm#researchds4.c is a narrow Metal inference engine for DeepSeek V4 Flash. It is not a general GGUF runner and only supports the G…
Check-in5/7/2026, 9:42:21 PM@cocktailpeanutchecked in toOpenReel Videosha256:246ac4f0...cb93b9d0•1 check-inConfirmed on darwin · arm64 · apple m1 maxdarwinarm64GPU: apple m1 maxRAM: 64 GBCommit messages (2)cocktailpeanut/openreel—Add 9 filesbf0f1c3pinokio · 5/7/2026augani/openreel-video(app)—chore: replace Claude code review with Copilot code review1297b0dAugustus Otu · 5/7/2026Last by @cocktailpeanut•5/7/2026, 9:42:21 PM
Post5/6/2026, 12:46:22 AM@cocktailpeanutposted inRetrositeRetrosite: website history visualizer0 comments#utilityRetrosite is a local app for making visual timelines from old website captures. Type in a domain or page, and it helps …
Check-in5/5/2026, 2:34:04 PM@cocktailpeanutchecked in toRetrositesha256:4855a248...2a257f0e•2 check-insConfirmed on darwin · arm64 · apple m1 maxdarwinarm64GPU: apple m1 maxRAM: 64 GBCommit messages (1)krynsky/retrosite—update local how-to-use copydfeda44Mark Krynsky · 5/4/2026Last by @cocktailpeanut•5/5/2026, 2:34:04 PM
Post5/5/2026, 3:09:39 AM@cocktailpeanutposted inReClipReclip supported services0 comments#researchWas curious which sites are exactly supported. Turns out a lot. ReClip uses yt-dlp under the hood — one of the most com…
Check-in5/3/2026, 4:27:43 PM@cocktailpeanutchecked in toVoxCPMsha256:bd118e68...6e15cee4•2 check-insConfirmed on win32 · x64 · nvidia rtx a4500win32x64GPU: nvidia rtx a4500RAM: 28 GBVRAM: 20 GBCommit messages (2)ianmove/voxcpm2-pinokio-launcher—improve readme5c120b8iAnMove · 5/3/2026openbmb/voxcpm(app)—fix: handle LoRA rank mismatch during inference in lora_ft_webui19b6bf7liuxin · 4/28/2026Last by @cocktailpeanut•5/3/2026, 4:27:43 PM
Check-in5/3/2026, 4:27:29 PM@cocktailpeanutchecked in toVoxCPMsha256:bd118e68...6e15cee4•2 check-insConfirmed on darwin · arm64 · apple m1 maxdarwinarm64GPU: apple m1 maxRAM: 64 GBCommit messages (2)ianmove/voxcpm2-pinokio-launcher—improve readme5c120b8iAnMove · 5/3/2026openbmb/voxcpm(app)—fix: handle LoRA rank mismatch during inference in lora_ft_webui19b6bf7liuxin · 4/28/2026Last by @cocktailpeanut•5/3/2026, 4:27:43 PM
Post4/30/2026, 8:57:16 PM@cocktailpeanutposted inPhosphenePhosphene image2video + text2video examples5 commentsText-to-video Took around 16 minutes on my Mac M1 Max 64GB, but I'm sure newer machines are faster! Image to video Prom…
Check-in4/30/2026, 8:38:45 PM@cocktailpeanutchecked in toPhosphenesha256:f32a440e...fe01f123•1 check-inConfirmed on darwin · arm64 · apple m1 maxdarwinarm64GPU: apple m1 maxRAM: 64 GBCommit messages (2)mrbizarro/phosphene—panel: add 'No music' toggle for voice + ambient only392c72aSalo · 4/30/2026dgrauet/ltx-2-mlx(ltx-2-mlx)—chore: bump version to 0.2.09923736Damien Grauet · 4/30/2026Last by @cocktailpeanut•4/30/2026, 8:38:45 PM
Post4/25/2026, 5:40:03 PM@cocktailpeanutposted inTexturizerTexturizer lets you generate custom textured rigged mesh from any image and a seed mesh1 commentsTexturizer is a gradio app that lets you: 1. Take any rigged mesh 2. Add any custom image 3. To generate a textured rig…
Post4/25/2026, 3:06:46 PM@cocktailpeanutposted inAI4AnimationPyAI4AnimationPy: Every frame generated, not authored.0 commentsI stumbled on this repo a few days ago and genuinely couldn't believe it wasn't all over my feed. So I built a way for …
Post4/23/2026, 9:06:36 PM@cocktailpeanutposted inStripperStripper: strip out "Made with AI" tags from images0 commentsI made a web app + agent-ready CLI for stripping out the "Made with AI" tag from images you upload to X (along with all…
Post4/21/2026, 6:25:40 PM@cocktailpeanutposted inEuphonyEuphony: browse all your Codex chat sessions in a web UI.1 commentsOpenAI just open sourced Euphony, a minimal web UI to browse and search all your Codex sessions . Works on ALL OS (Mac,…