SimpleTuner
AGENTS.md3k starsChanged 18 days agoAGPL-3.0View on GitHub
- Commits and pushes
Trending
More talk lately.about the whole repository
Who's talking about bghira/SimpleTuner
- ostris/ai-toolkit“Misinterpretation of attention masking”GitHub · Oct 6, 2024 · 5 reactions
- huggingface/diffusers“Full support for Flux attention masking”GitHub · Dec 11, 2024 · 4 reactions
- Comfy-Org/ComfyUI“Support fused to_qkv LoKR and LoRA loras by splitting them per projection”GitHub · Oct 7, 2026 · 1 reactions
- Stack Overflow“Cannot merge Lora weights back to the Flux Dev base model”Stack Overflow · Oct 29, 2024 · 1 votes
- @dailygithubtrends.bsky.social“今日のGitHubトレンド bghira/SimpleTuner SimpleTunerは、トレーニング最適化のための実験的なスクリプトをまとめたリポジトリです。 …”Bluesky · Aug 8, 2024 · 1 likes
The biggest 5 of 25 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 25
Talked about on GitHub, Bluesky and Stack Overflow (25 times).
On GitHub · 23
- Oct 6, 2024Misinterpretation of attention masking — ostris/ai-toolkit5 reactions · 2 comments
- Dec 11, 2024Full support for Flux attention masking — huggingface/diffusers4 reactions · 3 comments
- Oct 7, 2026Support fused to_qkv LoKR and LoRA loras by splitting them per projection — Comfy-Org/ComfyUI1 reaction · 13 comments
- Oct 9, 2026[P2/LoRA] Modern Trainer Adapter: FLUX.2 / Qwen-Image-2.1等の最新architectureとSimpleTuner・AI Toolkit・LyCORISを統合する — tomiya7688/comfyUI_support_tools0 reactions
- Sep 10, 2026Krea 2 with DoKR (LoKR + DoRA) has [WARNING] lora key not loaded — Comfy-Org/ComfyUI0 reactions · 4 comments
18 more on GitHub
- Sep 4, 2026Version 4.0.0 doesn't work with SimpleTuner and torch.compile — KohakuBlueleaf/LyCORIS0 reactions · 6 comments
- Feb 7, 2026[Feature] Transformer Block Swap — unslothai/unsloth0 reactions · 2 comments
- Jan 20, 2026support Flux2 klein — modelscope/DiffSynth-Studio0 reactions
- Dec 22, 2025A suggestion for Kandinsky 5 Video/image Lora training. — tdrussell/diffusion-pipe0 reactions · 2 comments
- Dec 22, 2025A suggestion for Kandinsky 5 Video/image Lora training. — kohya-ss/musubi-tuner0 reactions · 1 comment
- Dec 18, 2025fix: more robust translation processing and token handling — AIGNE-io/aigne-doc-smith0 reactions · 3 comments
- Dec 16, 2025integrated with CREPA in simpletuner — vita-epfl/LayerSync0 reactions · 2 comments
- Dec 7, 2025支持int8-quanto量化微调Qwen-Image-Edit-2509,48G显存即可微调🎉,训练脚本添加result_image_field_name参数. — modelscope/DiffSynth-Studio0 reactions · 1 comment
- Jun 3, 2025Video frames Transforms normalize 3 channel or 1 channel？transforms.Normalize([0.5], [0.5]) or transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]) — tdrussell/diffusion-pipe0 reactions · 2 comments
- Dec 27, 2024Re: Full-Rank Training for Sana 2k model on Human Image Dataset — NVlabs/Sana0 reactions · 6 comments
- Oct 11, 2024Prior model preservation — Nerogar/OneTrainer0 reactions · 27 comments
- Aug 24, 2024Got text encoder training to work. Please see if you could add it, along with quantization. — kohya-ss/sd-scripts0 reactions · 9 comments
- Aug 21, 2024Add From these — e2b-dev/awesome-ai-agents0 reactions · 1 comment
- Aug 15, 2024Bump diffusers from 0.27.2 to 0.30.0 — chux0519/ovgenai_rag0 reactions · 1 comment
- Aug 12, 2024Bump diffusers from 0.29.2 to 0.30.0 — openvinotoolkit/openvino.genai0 reactions · 2 comments
- Aug 12, 2024Bump diffusers[torch] from 0.29.2 to 0.30.0 in /app — hodanov/stable-diffusion-cli-on-modal0 reactions
- Aug 8, 2024Flux Lora from SimpleTuner training not working with ComfyUI — Comfy-Org/ComfyUI0 reactions · 8 comments
- Jul 20, 2024[Bug]: SD3 LoRA — AUTOMATIC1111/stable-diffusion-webui0 reactions · 1 comment
On Bluesky · 1
- Aug 8, 2024今日のGitHubトレンド bghira/SimpleTuner SimpleTunerは、トレーニング最適化のための実験的なスクリプトをまとめたリポジトリです。 コードの可読性と理解しやすさを重視し、シンプルさを追求しています。… — @dailygithubtrends.bsky.social1 likes and repost
On Stack Overflow · 1
- Oct 29, 2024Cannot merge Lora weights back to the Flux Dev base model1 vote · 1 answer
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repositoryOne other file it gives its agents.
- CLAUDE.mdCLAUDE.md
The file
Show its rules and text
We split this AGENTS.md into the rules it gives an agent
31 rules. About 0 are common, 28 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈28
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.