novelai-python 0.7.11__tar.gz → 0.8.0__tar.gz

novelai_python-0.8.0/NOTICE.MD

@@ -0,0 +1,8 @@
+# NOTICE OF THIS PROJECT
+
+## MIT License
+
+The MIT license applies to the files in:
+
+    file: "src/novelai_python/sdk/ai/generate_image/__init__.py" from https://github.com/HanaokaYuzu/NovelAI-API
+    file: "src/novelai_python/tool/image_metadata/lsb_injector.py" from https://github.com/NovelAI/novelai-image-metadata

novelai_python-0.8.0/PKG-INFO

@@ -0,0 +1,368 @@
+Metadata-Version: 2.1
+Name: novelai-python
+Version: 0.8.0
+Summary: NovelAI Python Binding With Pydantic
+Author-Email: sudoskys <coldlando@hotmail.com>
+License: Apache License 2.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Project-URL: Repository, https://github.com/LlmKira/novelai-python/
+Project-URL: Issues, https://github.com/LlmKira/novelai-python/issues
+Requires-Python: >=3.12
+Requires-Dist: pydantic>=2.14
+Requires-Dist: curl-cffi>=0.16.3
+Requires-Dist: msgpack>=1.2
+Requires-Dist: Pillow>=12.3
+Requires-Dist: numpy>=2.5
+Requires-Dist: pynacl>=1.6
+Requires-Dist: tokenizers>=0.23
+Provides-Extra: server
+Requires-Dist: fastapi>=0.143; extra == "server"
+Requires-Dist: uvicorn[standard]>=0.54; extra == "server"
+Provides-Extra: testing
+Requires-Dist: novelai-python[server]; extra == "testing"
+Requires-Dist: httpx>=0.28; extra == "testing"
+Requires-Dist: pytest>=9.1; extra == "testing"
+Requires-Dist: pytest-asyncio>=1.4; extra == "testing"
+Description-Content-Type: text/markdown
+
+![banner](https://github.com/LlmKira/novelai-python/blob/dev/playground/banner-raw.png?raw=true)
+
+---
+
+[![PyPI version](https://badge.fury.io/py/novelai-python.svg)](https://badge.fury.io/py/novelai-python)
+[![Downloads](https://pepy.tech/badge/novelai_python)](https://pepy.tech/project/novelai_python)
+
+
+>**Declaration** (2025/06/04)
+>
+>**I have nothing to do with NovelAI.**
+>
+>Due to various considerations, such as NovelAI's confusing project architecture and "can't learn anything from it", this project will be in a *non-active* maintenance state. If you have any questions, please *raise an issue*.
+>
+>This project is designed to be a sample project for me to write Python SDK. It turns out that Pydantic is very powerful.
+>
+>*I will invest more time in open source projects that are more beneficial to society.*
+>
+
+✨ NovelAI api python sdk with Pydantic, modern and user-friendly.
+
+The goal of this repository is to use Pydantic to build legitimate requests to access
+the [NovelAI API service](https://image.novelai.net/docs).
+
+> Python >= 3.12 is required (tested on 3.12 – 3.14).
+
+### 📰 News
+
+- **NovelAI Diffusion V5** family: `nai-diffusion-5-full`, `-full-medium` (fast, 14 steps), `-curated` and their
+  `-inpainting` variants, with the web client's quality presets (`standard` / `light` / `none`) and negative
+  presets. Every model uses `params_version` 4 (`ucPresetId` / `qualityPresetId`) and the
+  `multipart/form-data` body the web client sends.
+- **Streaming**: `async for event in gen.request_stream(session)` on `/ai/generate-image-stream` yields
+  intermediate previews and the final image per sample.
+- New: character reference (V4.5), `EncodeVibe`, transparent background (V5), `Upscale` on the image host,
+  `UserData`, `TrialStatus`, `Priority`, `CreatePersistentToken`, the OpenAI-compatible text API (`/oa/v1`),
+  and `GenerateImageInfer.from_metadata()` to rebuild a request from an image's metadata.
+- Fewer dependencies: pydantic, curl_cffi, msgpack, Pillow, numpy, pynacl and tokenizers. httpx, opencv,
+  argon2-cffi, ftfy/regex and `bchlib` are gone (`bchlib` has no Python 3.14 wheel; a NumPy BCH codec
+  replaces it).
+- Optional local image budget (`limiter=True`, see below).
+
+### ⬆️ Upgrading from 0.7
+
+Some changes do not raise an error, so check these when you upgrade:
+
+- **`HTTP(S)_PROXY` is ignored.** Sessions use `trust_env=False`, so a system proxy no longer routes NovelAI
+  traffic by accident. Pass `proxy="http://user:pass@host:port"` to the credential (`ApiCredential`,
+  `LoginCredential`, ...) or to `Login`; tokenizer downloads and tag suggestions read `NOVELAI_PROXY`.
+- **The default model is V5** (`nai-diffusion-5-full`) in `GenerateImageInfer` and `build_generate`.
+- **Images come back as PNG** by default (`image_format`), with the metadata in text chunks; set `parameters.image_format = ImageFormat.WEBP` for smaller files.
+- **`auto_text`** (V5 only, on by default): quoted text in the prompt is appended as a `, teXt: ...` block, as
+  novelai.net does. Pass `auto_text=False` to send the prompt untouched.
+- **Image and user endpoints moved to `image.novelai.net`**; `api.novelai.net` rejects third-party clients
+  there.
+- **Browser identity**: requests carry the headers of Chrome 155 on Windows, as the web client sends them.
+  Accept-Language is English (`en-US,en;q=0.9`) unless the credential says otherwise:
+  `ApiCredential(..., accept_language="en-sg")` (see `ACCEPT_LANGUAGES`) or a full header value.
+- **The image budget is off by default.** Pass `limiter=True` to `request()` / `request_stream()` for the
+  process-wide budget (`NOVELAI_DAILY_IMAGE_LIMIT`, default 2500 per 24h, saved to
+  `~/.novelai_python/image_limit.json`), or a `DailyImageLimiter` of your own. The budget is shared by all
+  tokens and by every limiter, in any process, that uses the same state file.
+- **Server: `POST /ai/augment-image` takes the image as the request body** (`application/octet-stream`); the
+  other fields stay query parameters. Send `Authorization: Bearer <token>` or the bare token.
+
+- [New Model. No Restrictions. V4.5 Full Is Here.](https://blog.novelai.net/novelai-diffusion-v4-5-full-release-678318c86205)
+- [NovelAI Diffusion V4.5 Curated is Here!](https://blog.novelai.net/novelai-diffusion-v4-5-curated-is-here-9e5ba1f628f3)
+- [Image Generation Model Release — NovelAI Anime Diffusion V4 Curated Preview (EN)](https://blog.novelai.net/release-novelai-anime-diffusion-v4-curated-preview-en-ca4b0b11e671)
+- [Tutorial: Creating Consistent Characters with NovelAI Diffusion Anime [Female]](https://blog.novelai.net/tutorial-en-creating-consistent-characters-with-novelai-diffusion-anime-female-538b4b678a4e)
+
+### 📦 Usage
+
+```shell
+pip -U install novelai-python
+```
+
+All API users must adhere to the NovelAI Terms of Service: https://novelai.net/terms.
+
+**More examples can be found in the [playground](https://github.com/LlmKira/novelai-python/tree/main/playground)
+directory, read code as documentation.**
+
+```python
+import asyncio
+import os
+
+from pydantic import SecretStr
+
+from novelai_python import GenerateImageInfer, ImageGenerateResp, ApiCredential
+from novelai_python.sdk.ai.generate_image import Model, Character, Sampler, UCPreset
+from novelai_python.sdk.ai.generate_image.schema import PositionMap
+
+session = ApiCredential(api_token=SecretStr(os.getenv("NOVELAI_JWT")))  # pst-***
+# For security reasons, storing user credentials in plaintext is strongly discouraged.
+
+prompt = "2girls, fisheye, closeup, from above"
+
+
+async def main():
+    gen = GenerateImageInfer.build_generate(
+        prompt=prompt,
+        model=Model.NAI_DIFFUSION_5_FULL,  # or NAI_DIFFUSION_4_5_FULL
+        character_prompts=[
+            Character(
+                prompt="1girl, head tilt, short hair, black hair, grey eyes, small breasts, looking at viewer",
+                uc="red hair",
+                center=PositionMap.B2
+            ),
+            Character(
+                prompt="1girl, fox ears, fox tail, white hair, white tail, white ears",
+                uc="black hair",
+                center=PositionMap.D2
+            )
+        ],
+        sampler=Sampler.K_EULER_ANCESTRAL,
+        ucPreset=UCPreset.TYPE0,
+        # Recommended, using preset negative_prompt depends on selected model
+        qualityToggle=True,
+        decrisp_mode=False,
+        variety_boost=True,
+        furry_mode=False,
+        # Checkbox in novelai.net
+    )
+    cost = gen.calculate_cost(is_opus=True)
+    print(f"charge: {cost} if you are vip3")
+    resp = await gen.request(session=session)  # raises DailyLimitExceeded once the local budget is spent
+    resp: ImageGenerateResp
+    print(resp.meta)
+    print(resp.save("./output"))  # auto-download every returned image
+
+    # streaming previews (V5 family)
+    async for event in gen.request_stream(session=session):
+        if event.is_final:
+            open(f"./output/sample_{event.samp_ix}.webp", "wb").write(event.image)
+        elif event.event_type == "intermediate":
+            print("preview", event.samp_ix, "step", event.step_ix, len(event.image), "bytes")
+
+
+loop = asyncio.get_event_loop()
+loop.run_until_complete(main())
+
+```
+
+#### 🔋 Anlas / limit monitoring
+
+```python
+from novelai_python import Subscription, UserData, TrialStatus, get_default_limiter
+
+sub = await Subscription().request(session=session)
+print(sub.anlas_left, sub.tier_name, sub.is_unlimited_image_generation)
+
+data = await UserData().request(session=session)  # subscription + information in one call
+print(data.anlas_left)
+
+trial = await TrialStatus().request(session=session)
+print(trial.trialImagesLeft)
+
+# only when requests opt in with limiter=True
+print(get_default_limiter().status())  # {'limit': 2500, 'used': ..., 'remaining': ..., 'reset_at': ...}
+```
+
+`sub.usage` is the Opus V5 usage bar: `percent`, `purchasedPercent` (bought extra, 0-300),
+`isNegative`, `timeUntilNextPercent`. `Priority().request(session)` returns the task priority balance;
+`CreatePersistentToken(overwrite=True).request(jwt_session)` creates a `pst-...` API key.
+
+#### 🖼️ Transparent background, character reference, vibes
+
+```python
+from novelai_python import CharacterReference, EncodeVibe, GenerateImageInfer
+from novelai_python.sdk.ai._enum import Model
+
+# V5: "Transparent BG" of the web client (tag before the quality suffix + straight alpha)
+gen = GenerateImageInfer.build_generate("1girl, standing", transparent_background=True)
+
+# V4.5: Precise Reference (character / style / costume / character&style / delta)
+gen = GenerateImageInfer.build_generate(
+    "1girl", model=Model.NAI_DIFFUSION_4_5_FULL,
+    character_references=[CharacterReference(image=open("ref.png", "rb").read(), fidelity=0.8)],
+)
+
+# V4 / V4.5 vibe transfer takes encoded vibes: encode once, reuse the result
+vibe = await EncodeVibe(image=open("vibe.png", "rb").read(), information_extracted=0.7).request(session)
+gen = GenerateImageInfer.build_generate(
+    "1girl", model=Model.NAI_DIFFUSION_4_5_FULL,
+    reference_image_multiple=[vibe.vibe_b64], reference_strength_multiple=[0.6],
+    reference_information_extracted_multiple=[0.7],
+)
+```
+
+V5 has no vibe transfer and no character reference; it takes up to 32 characters (V4/V4.5: 6).
+
+Environment:
+
+| variable | default | meaning |
+|---|---|---|
+| `NOVELAI_DAILY_IMAGE_LIMIT` | `2500` | images per 24h window, `0` disables |
+| `NOVELAI_LIMIT_STATE_FILE` | `~/.novelai_python/image_limit.json` | where the counter is persisted |
+
+#### 📦 LLM
+
+```python
+import asyncio
+import os
+
+from pydantic import SecretStr
+
+from novelai_python import APIError, LoginCredential
+from novelai_python.sdk.ai.generate import TextLLMModel, LLM, get_default_preset, AdvanceLLMSetting
+from novelai_python.sdk.ai.generate._enum import get_model_preset
+
+username = os.getenv("NOVELAI_USER", None)
+assert username is not None
+# credential = JwtCredential(jwt_token=SecretStr(jwt))
+login_credential = LoginCredential(
+    username=os.getenv("NOVELAI_USER"),
+    password=SecretStr(os.getenv("NOVELAI_PASS"))
+)
+
+
+async def chat(prompt: str):
+    try:
+        model = TextLLMModel.ERATO  # llama3
+        parameters = get_default_preset(model).parameters
+        agent = LLM.build(
+            prompt=prompt,
+            model=model,
+            # parameters=None,  # Auto Select or get from preset
+            parameters=get_model_preset(TextLLMModel.ERATO).get_all_presets()[0].parameters,  # Select from enum preset
+            advanced_setting=AdvanceLLMSetting(
+                min_length=1,
+                max_length=None,  # Auto
+            )
+        )
+        # NOTE:parameter > advanced_setting, which logic in generate/__init__.py
+        # If you not pass the parameter, it will use the default preset.
+        # So if you want to set the generation params, you should pass your own params.
+        # Only if you want to use some params not affect the generation, you can use advanced_setting.
+        result = await agent.request(session=login_credential)
+    except APIError as e:
+        raise Exception(f"Error: {e.message}")
+    print(f"Result: \n{result.text}")
+
+
+loop = asyncio.get_event_loop()
+loop.run_until_complete(chat("Hello"))
+```
+
+OpenAI-compatible text API (`text.novelai.net/oa/v1`), responses in OpenAI format:
+
+```python
+from novelai_python import OAIChatCompletion, OAIChatMessage, OAIModels
+
+models = await OAIModels().request(session)
+req = OAIChatCompletion(model=models.data[0].id, messages=[OAIChatMessage(role="user", content="Hello")])
+print((await req.request(session))["choices"][0]["message"]["content"])
+async for chunk in req.stream(session):
+    print(chunk["choices"][0]["delta"].get("content", ""), end="")
+```
+
+#### 📦 Random Prompt
+
+```python
+from novelai_python.tool.random_prompt import RandomPromptGenerator
+
+generator = RandomPromptGenerator()
+for i in range(10):
+    print(generator.generate_common_tags(nsfw=False))
+    print(generator.generate_scene_tags())
+    print(generator.generate_scene_composition())
+    print(generator.get_holiday_themed_tags())
+```
+
+#### 📦 Run A Server
+
+```shell
+pip install "novelai-python[server]"
+python3 -m novelai_python.server -h '127.0.0.1' -p 7888
+```
+
+#### 📦 Tokenizer
+
+```python
+from novelai_python._enum import get_tokenizer_model, TextLLMModel, TextTokenizerGroup
+from novelai_python.tokenizer import NaiTokenizer
+
+# Through llm model name to get the tokenizer
+tokenizer_package = NaiTokenizer(get_tokenizer_model(TextLLMModel.ERATO))
+# Directly use the tokenizer
+clip_tokenizer = NaiTokenizer(TextTokenizerGroup.CLIP)
+
+# Tokenize a text
+t_text = "a fox jumped over the lazy dog"
+encode_tokens = tokenizer_package.encode(t_text)
+print(tokenizer_package.tokenize_text(t_text))
+print(f"Tokenized text: {encode_tokens}")
+print(tokenizer_package.decode(tokenizer_package.encode(t_text)))
+
+```
+
+### 🔨 Roadmap
+
+- [x] tool.random_prompt
+- [x] tool.paint_mask
+- [x] tool.image_metadata
+- [x] tokenizer
+- [x] /ai/generate-image
+- [x] /user/subscription
+- [x] /user/login
+- [x] /user/information
+- [x] /ai/upscale
+- [x] /ai/generate-image/suggest-tags
+- [x] /ai/generate-voice
+- [x] /ai/generate-stream
+- [x] /ai/generate
+- [x] /ai/augment-image
+- [ ] /ai/annotate-image
+- [ ] /ai/classify
+- [ ] /ai/generate-prompt
+
+> GenerateImageInfer.calculate_cost is correct in most cases, but please request account information to get accurate
+> consumption information.
+
+> This repo is maintained by me personally now. If you have any questions, please feel free to open an issue.
+
+## 🚫 About Nsfw
+
+You might need some solutions for identifying NSFW content and adding a mosaic to prevent operational mishaps.
+
+https://dghs-imgutils.deepghs.org/main/api_doc/detect/nudenet.html
+
+https://dghs-imgutils.deepghs.org/main/api_doc/operate/censor.html
+
+## 🙏 Acknowledgements
+
+[novelai-api](https://github.com/Aedial/novelai-api)
+
+[NovelAI-API](https://github.com/HanaokaYuzu/NovelAI-API)
+
+

novelai_python-0.7.11/PKG-INFO → novelai_python-0.8.0/README.md

@@ -1,41 +1,3 @@
-Metadata-Version: 2.1
-Name: novelai-python
-Version: 0.7.11
-Summary: NovelAI Python Binding With Pydantic
-Author-Email: sudoskys <coldlando@hotmail.com>
-License: Apache License 2.0
-Project-URL: Repository, https://github.com/LlmKira/novelai-python/
-Project-URL: Issues, https://github.com/LlmKira/novelai-python/issues
-Requires-Python: >=3.9
-Requires-Dist: elara>=0.5.5
-Requires-Dist: loguru>=0.7.2
-Requires-Dist: pydantic-settings>=2.1.0
-Requires-Dist: pydantic>=2.9.0
-Requires-Dist: httpx>=0.26.0
-Requires-Dist: shortuuid>=1.0.11
-Requires-Dist: Pillow>=10.2.0
-Requires-Dist: curl-cffi>=0.11.3
-Requires-Dist: fastapi>=0.109.0
-Requires-Dist: uvicorn[standard]>=0.27.0.post1
-Requires-Dist: numpy>=1.24.4
-Requires-Dist: argon2-cffi>=23.1.0
-Requires-Dist: opencv-python>=4.8.1.78
-Requires-Dist: fake-useragent>=1.4.0
-Requires-Dist: tenacity>=8.2.3
-Requires-Dist: sentencepiece>=0.2.0
-Requires-Dist: pynacl>=1.5.0
-Requires-Dist: ftfy>=6.2.0
-Requires-Dist: regex>=2023.12.25
-Requires-Dist: tokenizers>=0.15.2
-Requires-Dist: json-repair>=0.29.4
-Requires-Dist: robust-downloader>=0.0.2
-Requires-Dist: bchlib>=2.1.3
-Requires-Dist: arrow>=1.3.0
-Provides-Extra: testing
-Requires-Dist: pytest>=7.4.4; extra == "testing"
-Requires-Dist: pytest-asyncio>=0.23.4; extra == "testing"
-Description-Content-Type: text/markdown
-
 ![banner](https://github.com/LlmKira/novelai-python/blob/dev/playground/banner-raw.png?raw=true)
 
 ---
@@ -58,12 +20,49 @@ Description-Content-Type: text/markdown
 ✨ NovelAI api python sdk with Pydantic, modern and user-friendly.
 
 The goal of this repository is to use Pydantic to build legitimate requests to access
-the [NovelAI API service](https://api.novelai.net/docs).
+the [NovelAI API service](https://image.novelai.net/docs).
 
-> Python >= 3.9 <3.13 is required.
+> Python >= 3.12 is required (tested on 3.12 – 3.14).
 
 ### 📰 News
 
+- **NovelAI Diffusion V5** family: `nai-diffusion-5-full`, `-full-medium` (fast, 14 steps), `-curated` and their
+  `-inpainting` variants, with the web client's quality presets (`standard` / `light` / `none`) and negative
+  presets. Every model uses `params_version` 4 (`ucPresetId` / `qualityPresetId`) and the
+  `multipart/form-data` body the web client sends.
+- **Streaming**: `async for event in gen.request_stream(session)` on `/ai/generate-image-stream` yields
+  intermediate previews and the final image per sample.
+- New: character reference (V4.5), `EncodeVibe`, transparent background (V5), `Upscale` on the image host,
+  `UserData`, `TrialStatus`, `Priority`, `CreatePersistentToken`, the OpenAI-compatible text API (`/oa/v1`),
+  and `GenerateImageInfer.from_metadata()` to rebuild a request from an image's metadata.
+- Fewer dependencies: pydantic, curl_cffi, msgpack, Pillow, numpy, pynacl and tokenizers. httpx, opencv,
+  argon2-cffi, ftfy/regex and `bchlib` are gone (`bchlib` has no Python 3.14 wheel; a NumPy BCH codec
+  replaces it).
+- Optional local image budget (`limiter=True`, see below).
+
+### ⬆️ Upgrading from 0.7
+
+Some changes do not raise an error, so check these when you upgrade:
+
+- **`HTTP(S)_PROXY` is ignored.** Sessions use `trust_env=False`, so a system proxy no longer routes NovelAI
+  traffic by accident. Pass `proxy="http://user:pass@host:port"` to the credential (`ApiCredential`,
+  `LoginCredential`, ...) or to `Login`; tokenizer downloads and tag suggestions read `NOVELAI_PROXY`.
+- **The default model is V5** (`nai-diffusion-5-full`) in `GenerateImageInfer` and `build_generate`.
+- **Images come back as PNG** by default (`image_format`), with the metadata in text chunks; set `parameters.image_format = ImageFormat.WEBP` for smaller files.
+- **`auto_text`** (V5 only, on by default): quoted text in the prompt is appended as a `, teXt: ...` block, as
+  novelai.net does. Pass `auto_text=False` to send the prompt untouched.
+- **Image and user endpoints moved to `image.novelai.net`**; `api.novelai.net` rejects third-party clients
+  there.
+- **Browser identity**: requests carry the headers of Chrome 155 on Windows, as the web client sends them.
+  Accept-Language is English (`en-US,en;q=0.9`) unless the credential says otherwise:
+  `ApiCredential(..., accept_language="en-sg")` (see `ACCEPT_LANGUAGES`) or a full header value.
+- **The image budget is off by default.** Pass `limiter=True` to `request()` / `request_stream()` for the
+  process-wide budget (`NOVELAI_DAILY_IMAGE_LIMIT`, default 2500 per 24h, saved to
+  `~/.novelai_python/image_limit.json`), or a `DailyImageLimiter` of your own. The budget is shared by all
+  tokens and by every limiter, in any process, that uses the same state file.
+- **Server: `POST /ai/augment-image` takes the image as the request body** (`application/octet-stream`); the
+  other fields stay query parameters. Send `Authorization: Bearer <token>` or the bare token.
+
 - [New Model. No Restrictions. V4.5 Full Is Here.](https://blog.novelai.net/novelai-diffusion-v4-5-full-release-678318c86205)
 - [NovelAI Diffusion V4.5 Curated is Here!](https://blog.novelai.net/novelai-diffusion-v4-5-curated-is-here-9e5ba1f628f3)
 - [Image Generation Model Release — NovelAI Anime Diffusion V4 Curated Preview (EN)](https://blog.novelai.net/release-novelai-anime-diffusion-v4-curated-preview-en-ca4b0b11e671)
@@ -84,14 +83,12 @@ directory, read code as documentation.**
 import asyncio
 import os
 
-from dotenv import load_dotenv
 from pydantic import SecretStr
 
 from novelai_python import GenerateImageInfer, ImageGenerateResp, ApiCredential
 from novelai_python.sdk.ai.generate_image import Model, Character, Sampler, UCPreset
 from novelai_python.sdk.ai.generate_image.schema import PositionMap
 
-load_dotenv()
 session = ApiCredential(api_token=SecretStr(os.getenv("NOVELAI_JWT")))  # pst-***
 # For security reasons, storing user credentials in plaintext is strongly discouraged.
 
@@ -101,7 +98,7 @@ prompt = "2girls, fisheye, closeup, from above"
 async def main():
     gen = GenerateImageInfer.build_generate(
         prompt=prompt,
-        model=Model.NAI_DIFFUSION_4_5_FULL,
+        model=Model.NAI_DIFFUSION_5_FULL,  # or NAI_DIFFUSION_4_5_FULL
         character_prompts=[
             Character(
                 prompt="1girl, head tilt, short hair, black hair, grey eyes, small breasts, looking at viewer",
@@ -125,12 +122,17 @@ async def main():
     )
     cost = gen.calculate_cost(is_opus=True)
     print(f"charge: {cost} if you are vip3")
-    resp = await gen.request(session=session)
+    resp = await gen.request(session=session)  # raises DailyLimitExceeded once the local budget is spent
     resp: ImageGenerateResp
     print(resp.meta)
-    file = resp.files[0]
-    with open(file[0], "wb") as f:
-        f.write(file[1])
+    print(resp.save("./output"))  # auto-download every returned image
+
+    # streaming previews (V5 family)
+    async for event in gen.request_stream(session=session):
+        if event.is_final:
+            open(f"./output/sample_{event.samp_ix}.webp", "wb").write(event.image)
+        elif event.event_type == "intermediate":
+            print("preview", event.samp_ix, "step", event.step_ix, len(event.image), "bytes")
 
 
 loop = asyncio.get_event_loop()
@@ -138,20 +140,73 @@ loop.run_until_complete(main())
 
 ```
 
+#### 🔋 Anlas / limit monitoring
+
+```python
+from novelai_python import Subscription, UserData, TrialStatus, get_default_limiter
+
+sub = await Subscription().request(session=session)
+print(sub.anlas_left, sub.tier_name, sub.is_unlimited_image_generation)
+
+data = await UserData().request(session=session)  # subscription + information in one call
+print(data.anlas_left)
+
+trial = await TrialStatus().request(session=session)
+print(trial.trialImagesLeft)
+
+# only when requests opt in with limiter=True
+print(get_default_limiter().status())  # {'limit': 2500, 'used': ..., 'remaining': ..., 'reset_at': ...}
+```
+
+`sub.usage` is the Opus V5 usage bar: `percent`, `purchasedPercent` (bought extra, 0-300),
+`isNegative`, `timeUntilNextPercent`. `Priority().request(session)` returns the task priority balance;
+`CreatePersistentToken(overwrite=True).request(jwt_session)` creates a `pst-...` API key.
+
+#### 🖼️ Transparent background, character reference, vibes
+
+```python
+from novelai_python import CharacterReference, EncodeVibe, GenerateImageInfer
+from novelai_python.sdk.ai._enum import Model
+
+# V5: "Transparent BG" of the web client (tag before the quality suffix + straight alpha)
+gen = GenerateImageInfer.build_generate("1girl, standing", transparent_background=True)
+
+# V4.5: Precise Reference (character / style / costume / character&style / delta)
+gen = GenerateImageInfer.build_generate(
+    "1girl", model=Model.NAI_DIFFUSION_4_5_FULL,
+    character_references=[CharacterReference(image=open("ref.png", "rb").read(), fidelity=0.8)],
+)
+
+# V4 / V4.5 vibe transfer takes encoded vibes: encode once, reuse the result
+vibe = await EncodeVibe(image=open("vibe.png", "rb").read(), information_extracted=0.7).request(session)
+gen = GenerateImageInfer.build_generate(
+    "1girl", model=Model.NAI_DIFFUSION_4_5_FULL,
+    reference_image_multiple=[vibe.vibe_b64], reference_strength_multiple=[0.6],
+    reference_information_extracted_multiple=[0.7],
+)
+```
+
+V5 has no vibe transfer and no character reference; it takes up to 32 characters (V4/V4.5: 6).
+
+Environment:
+
+| variable | default | meaning |
+|---|---|---|
+| `NOVELAI_DAILY_IMAGE_LIMIT` | `2500` | images per 24h window, `0` disables |
+| `NOVELAI_LIMIT_STATE_FILE` | `~/.novelai_python/image_limit.json` | where the counter is persisted |
+
 #### 📦 LLM
 
 ```python
 import asyncio
 import os
 
-from dotenv import load_dotenv
 from pydantic import SecretStr
 
 from novelai_python import APIError, LoginCredential
 from novelai_python.sdk.ai.generate import TextLLMModel, LLM, get_default_preset, AdvanceLLMSetting
 from novelai_python.sdk.ai.generate._enum import get_model_preset
 
-load_dotenv()
 username = os.getenv("NOVELAI_USER", None)
 assert username is not None
 # credential = JwtCredential(jwt_token=SecretStr(jwt))
@@ -189,6 +244,18 @@ loop = asyncio.get_event_loop()
 loop.run_until_complete(chat("Hello"))
 ```
 
+OpenAI-compatible text API (`text.novelai.net/oa/v1`), responses in OpenAI format:
+
+```python
+from novelai_python import OAIChatCompletion, OAIChatMessage, OAIModels
+
+models = await OAIModels().request(session)
+req = OAIChatCompletion(model=models.data[0].id, messages=[OAIChatMessage(role="user", content="Hello")])
+print((await req.request(session))["choices"][0]["message"]["content"])
+async for chunk in req.stream(session):
+    print(chunk["choices"][0]["delta"].get("content", ""), end="")
+```
+
 #### 📦 Random Prompt
 
 ```python
@@ -205,7 +272,7 @@ for i in range(10):
 #### 📦 Run A Server
 
 ```shell
-pip install novelai_python
+pip install "novelai-python[server]"
 python3 -m novelai_python.server -h '127.0.0.1' -p 7888
 ```