Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
Commits on main
Studio: add audio translations and list audio workflows in /v1/models (#12817)
7db04e4 Etherl committed 1 month ago
Read the API monitor unload button's disabled terms, not its exact spelling (#12858)
b71c11f Daniel Han committed 1 month ago
Studio Desktop: stop the launch-time PATH probe from rewriting shell history (#12846)
10b39da Daniel Han committed 1 month ago
tests: make the torchcodec provenance and mirror repair tests hermetic (#12850)
dc10bb5 Daniel Han committed 1 month ago
Studio: size host RAM from the container's cgroup, and re-measure the MiniMax-H3 floor (#12854)
1fea7ed Daniel Han committed 1 month ago
install.ps1: guard the mirror env restore in the outer finally (#12849)
7cb49da Daniel Han committed 1 month ago
Studio: show audio clip details, playback and runs in the Library (#12814)
9a43c1b Etherl committed 1 month ago
Studio: sandbox level picker and Settings > Sandbox cleanup (#12855)
a601a26 Michael Han committed 1 month ago
Studio: fine-tune Laya and Cloudflare Clef decision models and serve them (#12585)
6df2e23 Nilay committed 1 month ago
Build flex attention masks without graph breaks under torch.compile (#12837)
4eef011 Daniel Han committed 1 month ago
Studio: fix locale parity on main (Swedish sandbox strings, Manage files) (#12844)
dba2873 Daniel Han committed 1 month ago
Studio: sample Qwen-Image-2.1 and FLUX.1 dev at ComfyUI's fixed sigma schedule (#12838)
405efd2 Daniel Han committed 1 month ago
Studio: clone with 13 more audio.cpp models, convert with Tone-Color VC (#12822)
cdb5d55 Etherl committed 1 month ago
Studio: tighten the browser address bar and clear it while typing (#12852)
0a540cb Michael Han committed 1 month ago
Runtime encoding lint: exempt the reviewed PyAV codec open (#12831)
356891a Daniel Han committed 1 month ago
Call create_optimizer without a model in the embedding optim-bits test (#12697)
7e12999 Vineeth Sai Varikuntla committed 1 month ago
Studio: say when the audio runtime is not the release Studio installs (#12809)
1135dbd Etherl committed 1 month ago
Studio browser: mark the panel's fetches to unsloth.ai so its Cloudflare can skip the bot challenge (#12834)
4e30921 Daniel Han committed 1 month ago
Studio: close the MLX context compaction gaps left after #9399 (#12823)
72c55d6 Long Yixing committed 1 month ago
Studio: import Cursor, Claude Code and Codex conversations from Settings (#8561)
341a06b Tamsi committed 1 month ago
Studio: send audio clips, stems and transcripts to other Audio pages (#12811)
fed7810 Etherl committed 1 month ago
Pin qwen-image-layered's VAE config for the seam guard, and check coverage in Backend CI (#12843)
192fe85 Daniel Han committed 1 month ago
Studio: list every runnable audio.cpp-gguf model on its Audio pages (#12818)
aba956e Etherl committed 1 month ago
Studio: fix audio mic choice, reload page, tour copy and palette search (#12813)
dd04695 Etherl committed 1 month ago