commit 78d6533898a11af522cba343bfbfc2d75750eacb Author: syui Date: Sat Mar 29 17:32:07 2025 +0900 first diff --git a/.gitea/workflows/release.yml b/.gitea/workflows/release.yml new file mode 100644 index 0000000..d1b9c82 --- /dev/null +++ b/.gitea/workflows/release.yml @@ -0,0 +1,14 @@ +name: image exif remove + +on: + push: + +jobs: + release: + name: release + runs-on: ubuntu-latest + steps: + - name: Initialize + run: | + sudo apt-get install libimage-exiftool-perl + exiftool -all= -overwrite_original -r ./repos/comfyui diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..7176f4b --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +**.DS_Store diff --git a/README.md b/README.md new file mode 100644 index 0000000..78d8b92 --- /dev/null +++ b/README.md @@ -0,0 +1,16 @@ +# ai `ai` + +AI model `ai` + +the aim is to incorporate it into `aibot` and `aios`. + +|name|full|code|repo| +|---|---|---|---| +|ai|ai ai|aiai|https://git.syui.ai/ai/ai| +|os|ai os|aios|https://git.syui.ai/ai/os| +|bot|ai bot|aibot|https://git.syui.ai/ai/bot| +|at|ai|ai.syu.is|https://git.syui.ai/ai/at| + +```sh +$ ollama run syui/ai "hello" +``` diff --git a/card/1.png b/card/1.png new file mode 100644 index 0000000..aca1696 Binary files /dev/null and b/card/1.png differ diff --git a/card/1.webp b/card/1.webp new file mode 100644 index 0000000..0535346 Binary files /dev/null and b/card/1.webp differ diff --git a/card/2.png b/card/2.png new file mode 100644 index 0000000..f30f7d6 Binary files /dev/null and b/card/2.png differ diff --git a/card/2.webp b/card/2.webp new file mode 100644 index 0000000..be784c9 Binary files /dev/null and b/card/2.webp differ diff --git a/card/3.png b/card/3.png new file mode 100644 index 0000000..9a333bf Binary files /dev/null and b/card/3.png differ diff --git a/card/3.webp b/card/3.webp new file mode 100644 index 0000000..ab14807 Binary files /dev/null and b/card/3.webp differ diff --git a/card/readme.md b/card/readme.md new file mode 100644 index 0000000..6a5cfd9 --- /dev/null +++ b/card/readme.md @@ -0,0 +1,10 @@ +- [4:3] 2160x1620 +- [4:3] 1440x1080 +- [4:3] 1024×768 +- [4:3] 640×480 + +```bash +$ magick convert -resize 480x -quality 100 4.png 4.webp +$ magick convert -quality 100 1.png 1.webp +``` + diff --git a/docs/ja.md b/docs/ja.md new file mode 100644 index 0000000..b1d01c7 --- /dev/null +++ b/docs/ja.md @@ -0,0 +1,571 @@ +# ai + +AI modelの`ai`は、`aibot`や`aios`に組み込むことを目指します。 + +|name|full|code|repo| +|---|---|---|---| +|ai|ai ai|aiai|https://git.syui.ai/ai/ai| +|os|ai os|aios|https://git.syui.ai/ai/os| +|bot|ai bot|aibot|https://git.syui.ai/ai/bot| +|at|ai|ai.syu.is|https://git.syui.ai/ai/at| + +```sh +$ ollama run syui/ai "hello" +``` + +## 学習 + +物語を学習させます。特定の語彙を使用します。例えば「自分のことをアイという」などです。 + +> アイね、回答するの + +## できること + +基本的には`aibot`へのrequestに応じて、`comfyui`で画像や動画生成、LLMで回答を行います。 + +webからはatprotoを通じて実行されます。 + +```sh +[web]aiat --> [server]aios --> [at]aibot --> [ai]aiai +``` + +## 使用するもの + +- https://github.com/ollama/ollama +- https://github.com/n8n-io/n8n +- https://github.com/comfyanonymous/comfyui +- https://github.com/NVIDIA/cosmos +- https://github.com/stability-ai/stablediffusion +- https://github.com/unslothai/unsloth +- https://github.com/ml-explore/mlx-examples +- https://github.com/ggml-org/llama.cpp +- https://openai.github.io/openai-agents-python/mcp/ +- https://github.com/mannaandpoem/openmanus + +```json +{ + "model": [ "gemma3", "deepseek-r1" ], + "tag": [ "ollama", "LoRA", "unsloth", "open-webui", "n8n" ] +} +``` + +## AI + +### ollama + +```sh +# mac +$ brew install ollama +$ brew services restart ollama + +# windows +$ winget install ollama.ollama +$ ollama serve + +$ ollama pull gemma3:1b +$ ollama run gemma3:1b "hello" +``` + +### n8n + +```sh +# https://github.com/n8n-io/n8n/ +$ docker volume create n8n_data +$ docker run -it --rm --name n8n -p 5678:5678 -v n8n_data:/home/node/.n8n docker.n8n.io/n8nio/n8n +``` + +### webui + +```sh +$ winget install python.python.3.12 +$ python --version +$ python -m venv webui +$ cd webui +$ .\Scripts\activate +$ pip install open-webui +$ open-webui serve + +http://localhost:8080 +``` + +### LoRA + +apple siliconでLoRA(finetuning)するには`mlx_lm`を使用します。 + +```sh +$ brew install --cask anaconda +$ brew info anaconda +$ cd /opt/homebrew/Caskroom/anaconda/* +$ ./Anaconda3*.sh +``` + +`google/gemma-3-1b-it`を承認しておきます。 + +- https://huggingface.co/google/gemma-3-1b-it + +```sh +$ pip install -U "huggingface_hub[cli]" +# https://huggingface.co/settings/tokens +# Repositories permissions:Read access to contents of selected repos + +$ huggingface_hub login +``` + +```sh +$ conda create -n finetuning python=3.12 +$ conda activate finetuning +$ pip install mlx-lm +$ echo "{ \"model\": \"https://huggingface.co/google/gemma-3-1b-it\", \"data\": \"https://github.com/ml-explore/mlx-examples/tree/main/lora/data\" }"|jq . +$ git clone https://github.com/ml-explore/mlx-examples +$ model=google/gemma-3-1b-it +$ data=mlx-examples/lora/data +$ mlx_lm.lora --train --model $model --data $data --batch-size 3 + +$ ls adapters +adapter_config.json +adapters.safetensors +``` + +### unsloth + +windowsでLoRA(finetuning)するには`unsloth`を使います。 + +最も安定しているのは以下のverです。 + +```sh +$ nvidia-smi +$ nvcc --version + +# https://github.com/unslothai/notebooks/blob/main/unsloth_windows.ps1 +cuda: 12.4 +python: 3.11 +``` + +torchをcuda:12.8で使用する方法もあります。python:3.12を使用できます。しかし、unslothのinstallでは問題が発生しました。 + +```sh +$ winget install --scope machine nvidia.cuda --version 12.4.1 +$ winget install curl.curl +``` + +```sh +# https://docs.unsloth.ai/get-started/installing-+-updating/windows-installation +$ curl -sLO https://raw.githubusercontent.com/unslothai/notebooks/refs/heads/main/unsloth_windows.ps1 +$ powershell.exe -ExecutionPolicy Bypass -File .\unsloth_windows.ps1 +$ vim custom.py +``` + +上記はpwshでunsolthを使う方法ですが、wslを使ったほうがいいです。 + +```py +# https://docs.unsloth.ai/get-started/fine-tuning-guide +from unsloth import FastModel +import torch + +fourbit_models = [ + # 4bit dynamic quants for superior accuracy and low memory use + # https://docs.unsloth.ai/basics/tutorial-how-to-run-and-fine-tune-gemma-3 + # https://huggingface.co/unsloth/gemma-3-4b-it + "unsloth/gemma-3-1b-it-unsloth-bnb-4bit", + "unsloth/gemma-3-4b-it-unsloth-bnb-4bit", + "unsloth/gemma-3-12b-it-unsloth-bnb-4bit", + "unsloth/gemma-3-27b-it-unsloth-bnb-4bit", + + # Other popular models! + "unsloth/Llama-3.1-8B", + "unsloth/Llama-3.2-3B", + "unsloth/Llama-3.3-70B", + "unsloth/mistral-7b-instruct-v0.3", + "unsloth/Phi-4", +] # More models at https://huggingface.co/unsloth + +model, tokenizer = FastModel.from_pretrained( + model_name = "unsloth/gemma-3-4b-it", + max_seq_length = 2048, # Choose any for long context! + load_in_4bit = True, # 4 bit quantization to reduce memory + load_in_8bit = False, # [NEW!] A bit more accurate, uses 2x memory + full_finetuning = False, # [NEW!] We have full finetuning now! + # token = "hf_...", # use one if using gated models +) +model = FastModel.get_peft_model( + model, + finetune_vision_layers = False, # Turn off for just text! + finetune_language_layers = True, # Should leave on! + finetune_attention_modules = True, # Attention good for GRPO + finetune_mlp_modules = True, # SHould leave on always! + + r = 8, # Larger = higher accuracy, but might overfit + lora_alpha = 8, # Recommended alpha == r at least + lora_dropout = 0, + bias = "none", + random_state = 3407, +) +``` + +### mcp + +openai(chatgpt作ってるところ)がAIエージェントのmcpというprotocolを採用しています。 + +https://openai.github.io/openai-agents-python/mcp/ + +> MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools. + +### manus + +AIエージェントはmanusが有名ですが、manusを使わないopenmanusというものがあります。 + +これは、llmが複数で協調してタスクを行うように調整されたAIエージェントぽいです。manusを使わず、そのやり方を真似ている感じかと思います。 + +```sh +# https://github.com/mannaandpoem/openmanus +$ conda create -n open_manus python=3.12 +$ conda activate open_manus +$ git clone https://github.com/mannaandpoem/OpenManus.git +$ cd OpenManus +$ pip install -r requirements.txt + +$ cp config/config.example.toml config/config.toml +$ vim config/config.toml +``` + +```toml:config/config.toml +[llm] +model = "gpt-4o" +base_url = "https://api.openai.com/v1" +api_key = "sk-..." # Replace with your actual API key +max_tokens = 4096 +temperature = 0.0 +# Optional configuration for specific LLM models +[llm.vision] +model = "gpt-4o" +base_url = "https://api.openai.com/v1" +api_key = "sk-..." # Replace with your actual API key +``` + +```sh +$ python main.py +``` + +## comfyui + +https://github.com/comfyanonymous/comfyui + +- https://github.com/ltdrdata/comfyui-manager +- https://github.com/ltdrdata/comfyui-impact-pack + +開発者のmatrix roomが`comfyui_space:matrix.org`にあります。 + +https://app.element.io/#/room/#comfyui_space:matrix.org + +### install + +installは`git clone`から構築したほうがいいです。 + +```sh +# https://docs.comfy.org/installation/manual_install#nvidia:install-nightly +$ winget install python.python.3.12 +$ git clone https://github.com/comfyanonymous/comfyui +$ cd comfyui +$ python -m venv venv +$ Set-ExecutionPolicy RemoteSigned -Scope Process +$ venv\Scripts\activate +$ pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128 +$ python -m pip install --upgrade pip +$ pip install -r requirements.txt + +$ python main.py +http://localhost:8188 +``` + +comfyuiはnodeで書きますが`workflow`と呼ぶようです。jsonで保存されます。簡単にimportできます。 + +https://comfyanonymous.github.io/ComfyUI_examples/ + +基本構造としては、以下のとおりです。 + +```sh +./comfyui +├── main.py +├── custom_nodes # ここにpluginを入れる +│   └── comfyui-manager +└── models + └── checkpoints # ここにmodelを入れる + └── model.safetensors +``` + +1. modelは[comfyui-manager](https://github.com/ltdrdata/comfyui-manager)、または[civitai.com](https://civitai.com/models)からdlするといいです。 +2. workflowは[example](https://github.com/aimpowerment/comfyui-workflows)があります。また、[openart.ai](https://openart.ai/workflows/all)と連携できます。 +3. promptは[majinai.art](https://majinai.art/ja/)を参照してください。 + +例えば、`text-to-image.json`をworkflowに読み込んで、modelとpromptを書き換えて生成してみます。 + +```sh +# https://docs.comfy.org/get_started/first_generation +# このjsonをworkflowにimportします +$ curl -sLO https://raw.githubusercontent.com/Comfy-Org/docs/refs/heads/main/public/text-to-image.json +``` + +`1920x1080(1080p)`を生成しました。一部、ollamaでpromptを生成してもらっています。 + + + +```json +{ + "models": { + "checkpoints": "hsUltrahdCG_IIIEpic.safetensors", + "hsUltrahdCG_IIIEpic": "https://civitai.com/api/download/models/1456463?type=Model&format=SafeTensor" + }, + "prompt": { + "positive": "(portrait,portrait1.5, masterpiece:1.2, simple dress, full body, blonde hair, Round eyes, look at viewer, best quality:1.5, front view:1.10), (little child girl:1.5, stumpy child:1.3, smirk:1.10), narrow eyes:1.5, flat breasts:1.6, flat chest:1.6, flat hip:1.5, , AsianEyesEra:0.8, cinematic shadows:1.6, mouth close:1.5, cobblestone road, wearing strings:1.5, little child:1.8, little girl:1.8, long hair, Angel halo, White Dress, full body, Eye color is blue", + "negative": "breasts pubic hair, score_6, score_5, score_4, source_pony, (worst quality:1.8), (low quality:1.8), (normal quality:1.8), lowres, bad anatomy, bad hands, signature, watermarks, ugly, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, extra limb, missing limbs, bad-artist, depth of field, girls, 2girls, many girls, plural girls, mutiple girls, brown hair, black hair" + } +} +``` + +ollamaから生成されるpromptは、`show text -> string function -> [text]clip text encode(prompt)`で統合して`positive`に繋いでいます。上記のpromptに追加すると使用できますが、解説のため分けています。 + +gemmaから生成されているため、質問+回答に改行が挟まれて出力されています。これは適時、ollamaで使用するmodelの出力に合わせて加工します。今回は全文そのまま入れています。 + +```json +{ + "prompt": { + "positive": "You describe pictures. I will give you a brief description of the picture. You will describe the picture in intricate detail. Describe clothing, pose, expression, setting, lighting, and any other details you can think of. Use long descriptive sentences.You describe pictures. I will give you a brief description of the picture. You reply with comma separated keywords that describe the picture. Describe clothing, pose, expression, setting, and any other details you can think of. Use comma separated keywords. Do not use sentences. Use brevity. , cherry blossom, sakura tree, pink blossoms, petals falling, serene atmosphere, traditional kimono, elegant pose, soft lighting, dappled sunlight, peaceful scene, Japanese garden, tranquil setting, detailed foliage, pink hues, gentle breeze, traditional architecture, serene, calm, beautiful, springtime, delicate, romantic" + } +} +``` + +### exif + +出力された画像は`exif`が付いています。そこにはworkflowが全部保存されています。 + +```sh +$ exiftool -s -G -j ComfyUI_00001_.png +[ { "id": "xxx", "Composite:ImageSize": "1920x1080", "Composite:Megapixels": 2.1 } ] + +# exifを削除する +$ exiftool -all= -overwrite_original -r ./ComfyUI_00001_.png +[{}] +``` + +### model + +```json +{ + "models": { + "checkpoints": { + "sd_xl_base_1.0.safetensors": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0.safetensors", + "sd_xl_refiner_1.0.safetensors": "https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/blob/main/sd_xl_refiner_1.0.safetensors", + "v1-5-pruned.ckpt2": "https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned.ckpt", + "moeFussionV1.4.0_RICZ_vz.safetensors": "https://huggingface.co/JosefJilek/moeFussion/blob/main/moeFussionV1.4.0_RICZ_vz.safetensors", + "hsUltrahdCG_IIIEpic": "https://civitai.com/api/download/models/1456463?type=Model&format=SafeTensor" + }, + "vae": { + "wan_2.1_vae.safetensors": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors" + }, + "diffusion_models": { + "wan2.1_i2v_720p_14B_fp8_scaled.safetensors": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/diffusion_models/wan2.1_i2v_720p_14B_fp8_scaled.safetensors" + }, + "text_encoders": { + "umt5_xxl_fp8_e4m3fn_scaled.safetensors": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors" + }, + "clip_vision": { + "clip_vision_h.safetensors": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors" + }, + "loras": { + "StudioGhibli.Redmond-StdGBRRedmAF-StudioGhibli.safetensors": "https://huggingface.co/artificialguybr/StudioGhibli.Redmond-V2/blob/main/StudioGhibli.Redmond-StdGBRRedmAF-StudioGhibli.safetensors", + "Yoji_Shinkawa_Art_Style_Flux.safetensors": "https://civitai.com/api/download/models/912623?type=Model&format=SafeTensor" + }, + "upscalers": {}, + "other_models": {} + } +} +``` + +### torch(cuda:12.8)で問題が発生した場合 + +`cuda:12.8`で問題が発生した場合、こちらを参考にしてください。 + +私の環境だと問題は発生しませんでした。 + +```sh +$ cd ComfyUI/.venv/Scripts/ +$ ./python.exe -V +python:3.12 +``` + +`torch`のnightly versionは`cuda:12.8`に対応しています。 + +https://pytorch.org/get-started/locally/ + +```sh +$ pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128 +``` + +しかし、`torchaudio`などで衝突が発生します。衝突が発生する場合はversionを指定します。しかし、この方法で互換性が完全に解消されるわけではありません。 + +```sh +$ ./python.exe -m pip uninstall torch torchvision torchaudio -y +$ ./python.exe -m pip install --pre torch==2.7.0.dev20250306+cu128 torchvision==0.22.0.dev20250306+cu128 torchaudio==2.6.0.dev20250306+cu128 --index-url https://download.pytorch.org/whl/nightly/cu128 +``` + +ホイールファイルを使用すると安定するようです。 + +```sh +# https://huggingface.co/w-e-w/torch-2.6.0-cu128.nv +$ ./python.exe -m pip install torch-2.x.x+cu128-cp312-cp312-win_amd64.whl +$ ./python.exe -m pip install torchvision-x.x.x+cu128-cp312-cp312-win_amd64.whl +$ ./python.exe -m pip install torchaudio-x.x.x+cu128-cp312-cp312-win_amd64.whl + +$ ./python.exe -c "import torch; print(torch.cuda.is_available()); print(torch.__version__); print(torch.cuda.get_arch_list())" +``` + +### comfyui + ollama + +自動でpromptの生成を行います。ollamaのlocal llm modelを使用します。 + +- https://github.com/stavsap/comfyui-ollama +- https://github.com/pythongosssss/ComfyUI-Custom-Scripts + +`show text`のcustom nodeを使用するには`ComfyUI-Custom-Scripts`が必要です。 + +https://github.com/aimpowerment/comfyui-workflows/blob/main/ollama-txt2img-workflow.json + +nodeにある設定の方には以下の文章を載せておきます。 + +https://github.com/ScreamingHawk/comfyui-ollama-prompt-encode/blob/main/nodes/OllamaPromptGenerator.py + +```json +{ + "ollama-clip-prompt-encode": { + "prepend_tags": "You describe pictures. I will give you a brief description of the picture. You reply with comma separated keywords that describe the picture. Describe clothing, pose, expression, setting, and any other details you can think of. Use comma separated keywords. Do not use sentences. Use brevity.", + "text": "Under the cherry sakura tree" + } +} +``` + +### comfyuiで動画生成 + +#### cosmos + +nvidiaのcosmosを使った動画生成です。 + +https://comfyanonymous.github.io/ComfyUI_examples/cosmos/ + +```json +{ + "models": { + "text_encoders": { + "url": "https://huggingface.co/comfyanonymous/cosmos_1.0_text_encoder_and_VAE_ComfyUI/blob/main/text_encoders/oldt5_xxl_fp8_e4m3fn_scaled.safetensors" + }, + "vae": { + "url": "https://huggingface.co/comfyanonymous/cosmos_1.0_text_encoder_and_VAE_ComfyUI/blob/main/vae/cosmos_cv8x8x8_1.0.safetensors" + }, + "diffusion_models": { + "url": "https://huggingface.co/mcmonkey/cosmos-1.0/blob/main/Cosmos-1_0-Diffusion-7B-Video2World.safetensors" + } + } +} +``` + +```sh +$ curl -sLO https://comfyanonymous.github.io/ComfyUI_examples/cosmos/image_to_video_cosmos_7B.json +``` + +#### wan2.1 + +`cosmos`より`wan2.1`のほうがよい動画が生成できました。 + +https://blog.comfy.org/p/wan21-video-model-native-support + +```json +{ + "models": { + "diffusion_models": { + "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/diffusion_models/wan2.1_i2v_720p_14B_fp8_scaled.safetensors" + }, + "text_encoders": { + "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors" + }, + "clip_vision": { + "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors" + }, + "vae": { + "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors" + } + } +} +``` + +```sh +$ curl -sLO "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/example%20workflows_Wan2.1/image_to_video_wan_720p_example.json" +``` + +`720x480(480p)`相当を生成しました。 + + + +```json +{ + "prompt": { + "positive": "A girl walks in a beautiful and dreamy place. The wind is blowing. She looks up at the sky and sees the clouds slowly moving by, Cherry blossoms falling like snow", + "negative": "Overexposure, static, blurred details, subtitles, paintings, pictures, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, mutilated, redundant fingers, poorly painted hands, poorly painted faces, deformed, disfigured, deformed limbs, fused fingers, cluttered background, three legs, a lot of people in the background, upside down" + } +} +``` + +`1280x720(720p)`は時間がかかりすぎるのでおすすめしません。 + +### instantIDで同じ顔を使う + +[cubiq/ComfyUI_InstantID](https://github.com/cubiq/ComfyUI_InstantID)を使うことで、生成される画像に同じキャラクター(顔)を使用することができます。 + +なお、[Gourieff/ReActor](https://github.com/Gourieff/ComfyUI-ReActor)を併用することで、更に精度を高めることができます。 + +- ComfyUI_InstantID +- InstantID/ip-adapter +- InstantID/ControlNet + +```sh +$ python.exe -m pip install onnxruntime +``` + +`instantID`のinstallはかなり厄介です。依存関係が多く、errorが出やすいと思います。また、`model(checkpoints)`には`SDXL`に対応したものが必要です。 + +後述する`InstantID_depth.json`, `InstantID_basic.json`を動作させる事ができましたが、必要なものが何なのかは正確に理解出来ていません。 + +```sh +$ curl -sLO https://raw.githubusercontent.com/cubiq/ComfyUI_InstantID/refs/heads/main/examples/InstantID_depth.json +$ curl -sLO https://raw.githubusercontent.com/cubiq/ComfyUI_InstantID/refs/heads/main/examples/InstantID_basic.json +``` + +instantIDはseedをrandomにしないと同じ画像が生成されます。そのため、seedのpinを公開してrandomにつなげています。(comfyuiではnodeのpinをどう呼ぶのかわからない) + +### outlineをはっきりさせたい + +キャラクターのoutlineをはっきりさせたい時がある。これはprompotで調整すべきなのか、modelで調整すべきなのか、あるいはlayer(node)で調整すべきなのか。 + +- https://note.com/aicu/n/nacf66b92d2d5 + +`ComfyUI_LayerStyle`も使えるかも。 + +- https://github.com/chflame163/ComfyUI_LayerStyle + +### 部分的な修正 + +これは画像出力後に確認して手動で変更する方法になります。具体的には、部分をmaskで塗りつぶし、VAEで画像をエンコードし、それを潜在空間が認識できるコンテンツに変換し、その後マスク領域をノイズコンテンツとして再生成します。 + +[ref] + +- https://comfyui-wiki.com/ja/tutorial/basic/how-to-inpaint-an-image-in-comfyui +- https://docs.seaart.ai/guide-1/ri-ben-yu/2-ji-ben-ji-neng/2-10-wkufur/img2imgna +- https://www.digitalcreativeai.net/ja/post/how-use-powerful-flux1-tools-modify-images-comfyui + +輪っかの部分はキャラクターと離れると背景として認識されてしまいます。そのため絵として接続されている状態でなければいけません。 + + + +### ポーズを変更する + +これは`OpenPose`というものがあります。3d-modelでいうboneのようなものを動かしてポーズを指定します。 + +- https://comfyui-wiki.com/en/tutorial/advanced/how-to-use-openpose-controlnet-with-sd1.5 diff --git a/icon/ai.png b/icon/ai.png new file mode 100644 index 0000000..375a45f Binary files /dev/null and b/icon/ai.png differ diff --git a/repos/comfyui/model-list.json b/repos/comfyui/model-list.json new file mode 100644 index 0000000..b7d19af --- /dev/null +++ b/repos/comfyui/model-list.json @@ -0,0 +1,29 @@ +{ + "models": { + "checkpoints": { + "sd_xl_base_1.0.safetensors": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0.safetensors", + "sd_xl_refiner_1.0.safetensors": "https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/blob/main/sd_xl_refiner_1.0.safetensors", + "v1-5-pruned.ckpt2": "https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned.ckpt", + "moeFussionV1.4.0_RICZ_vz.safetensors": "https://huggingface.co/JosefJilek/moeFussion/blob/main/moeFussionV1.4.0_RICZ_vz.safetensors", + "hsUltrahdCG_IIIEpic": "https://civitai.com/api/download/models/1456463?type=Model&format=SafeTensor" + }, + "vae": { + "wan_2.1_vae.safetensors": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors" + }, + "diffusion_models": { + "wan2.1_i2v_720p_14B_fp8_scaled.safetensors": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/diffusion_models/wan2.1_i2v_720p_14B_fp8_scaled.safetensors" + }, + "text_encoders": { + "umt5_xxl_fp8_e4m3fn_scaled.safetensors": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors" + }, + "clip_vision": { + "clip_vision_h.safetensors": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors" + }, + "loras": { + "StudioGhibli.Redmond-StdGBRRedmAF-StudioGhibli.safetensors": "https://huggingface.co/artificialguybr/StudioGhibli.Redmond-V2/blob/main/StudioGhibli.Redmond-StdGBRRedmAF-StudioGhibli.safetensors", + "Yoji_Shinkawa_Art_Style_Flux.safetensors": "https://civitai.com/api/download/models/912623?type=Model&format=SafeTensor" + }, + "upscalers": {}, + "other_models": {} + } +} diff --git a/repos/comfyui/output/1.png b/repos/comfyui/output/1.png new file mode 100644 index 0000000..8ecbc3e Binary files /dev/null and b/repos/comfyui/output/1.png differ diff --git a/repos/comfyui/output/1.webp b/repos/comfyui/output/1.webp new file mode 100644 index 0000000..ec3f73d Binary files /dev/null and b/repos/comfyui/output/1.webp differ diff --git a/repos/comfyui/output/2.png b/repos/comfyui/output/2.png new file mode 100644 index 0000000..f26c89a Binary files /dev/null and b/repos/comfyui/output/2.png differ diff --git a/repos/comfyui/output/2.webp b/repos/comfyui/output/2.webp new file mode 100644 index 0000000..7a263d1 Binary files /dev/null and b/repos/comfyui/output/2.webp differ diff --git a/repos/comfyui/user/default/workflows/.keep b/repos/comfyui/user/default/workflows/.keep new file mode 100644 index 0000000..e69de29