![Telegram profile photo for Neurochan AI [Второй канал]](https://cdn.tgregister.com/av/83/83ea57d2f49876f73e07ce77edc65956356c276131609cef13fe8d22d99fc089.jpg)
Channel
@neurochan_tricks
On this record: Growth · Engagement · Reactions · Posts · Citations · Cite this entry
883subscribers
-5 since we began measuring on 7 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
| Telegram ID | -1002443215754 |
|---|---|
| Type | Channel |
| Username | @neurochan_tricks |
| Created | Between 1 September 2024 and 31 March 2025 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 8 August 2026 |
| Last confirmed live | 5 September 2026 |
| Measurements held | 6 |
| Confirmed unchanged | 1 time, most recently 5 September 2026 |
| On Telegram | t.me/neurochan_tricks |
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 5 Sept 2026, 15:18 | 883 | -2 |
| 28 Aug 2026, 17:43 | 885 | +8 |
| 22 Aug 2026, 04:26 | 877 | -4 |
| 14 Aug 2026, 21:26 | 881 | -7 |
| 8 Aug 2026, 01:05 | 888 | no change |
| 7 Aug 2026, 14:45 | 888 | first reading |
10 posts held, back to 29 September 2025 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 page of Telegram’s post history, 20 posts per page.
Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 10 posts for this entry, the most recent from 31 May 2026. An engagement rate over an empty window would be a number about nothing.
116 reactions across 10 posts, in 6 distinct kinds. The most used accounts for 50.9% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 👍 | 59 | 50.9% | |
| ❤ | 37 | 31.9% | |
| 💘 | 7 | 6.03% | |
| 🔥 | 7 | 6.03% | |
| ❤🔥 | 4 | 3.45% | |
| 👎 | 2 | 1.72% |
No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.
Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.
Coverage. Reactions were read on 10 of the 10 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 116 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 10 most recent posts we hold, published 29 September 2025 to 31 May 2026, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.
Особенности моделей генерации видео Wan 2.2 — модель для коротких анимаций по картинке. Без звука и диалогов, только одна сцена. Для хорошего результата нужен промпт из 30-60 слов, можно использовать формат тегов ("medium close-up shot, soft lighting, warm colors"). Может создавать видео до 6 секунд. LTX 2.3 — модель для кинематографичных видео с озвучкой. Умеет создавать атмосферный звук, музыку и озвучивать персо…
❤8💘3
Как работают «Режим Турбо» и «HD качество» для моделей Anima ♿️ При включенном Режиме Турбо мы применяем официальную Turbo Lora и уменьшаем кол-во сэмплов — это позволяет значительно сэкономить наши ресурсы, поэтому включение этой опции уменьшает стоимость генерации на 5 токенов Однако Turbo LoRA влияет на поведение самой модели: упрощаются детали, снижается точность следования подсказке Для моделей Anima-Base (по…
❤4
Токены — это виртуальная валюта, которая расходуется при генерациях в @neurochan_ai_bot При первом запуске бота ваш баланс будет равен 100 токенов Цены на генерации варьируются в зависимости от выбранного режима, модели или качества Модели Illustrious\NoobAI, а также кастомные модели — 10 токенов или 15 токенов в высоком HD качестве (для пользователей с Premium-подпиской цена всегда 10 токенов) Модели Anima Previ…
💘4❤3
⏰ Генерация партиями: как сэкономить время и получить хороший результат Очень редко можно получить качественный результат с 1 попытки, чаще всего приходится по несколько раз повторять один и тот же промпт😩 Чтобы не пришлось делать это вручную, в боте есть опция «Генерация партиями» Если нажать на кнопку в сообщении и включить её — бот будет генерировать 4 изображения за один подход, каждое с новым сидом Все 4 кар…
❤🔥4👍1
🧠 Генерируем селфи с вашими персонажами Всё, что нужно — закинуть картинку в режим «Умни обработки» и использовать промпт: Create an image of this character that looks like a selfie taken with an iPhone, keep the original facial expression and emotions. There should be no clear subject or specific composition just a casual, unintentio-nal snapshot. The image background should be just a little blurred from motion an…
❤12👍2
Рекомендации по промптам для LTX 2 https://ltx.io/model/model-blog/prompting-guide-for-ltx-2 Базовая инструкция по использованию в боте https://neurochan-ai.ru/articles/ltx2-guide.html
🔥7❤3
В чем разница между «Стандартной» и «Умной» обработкой фото в боте? Обычная (стандартная) генерация #img2img Берет ваше изображение, превращает его в «шум» и заново перерисовывает по текстовому промпту Таким образом, получается примерно такое же изображение, но с внесением небольших изменений Этот вариант не подходит, если например нужно "поменять цвет" или что-то добавить, т.к. нейросеть просто добавляет небольши…
❤6👍5
Инструмент Danbooru Tagger Доступен через команду /tools Создает подписи для изображений в формате danbooru тегов с точностью не ниже 40% Можно отправлять сразу как несколько файлов, так и несколько фото Если вы отправите файлом — бот пришлет ответ в виде txt с таким же названием как и у вашего файла Бот будет присылать результат ответом на сообщение, поэтому лучше отключите группировку в одно сообщение, чтобы ка…
👍27
#lora@neurochan_tricks #стиль@neurochan_tricks #Qwen Стили на Qwen! 1. <lora:2196092:1.0>, Q version，origami style, (стиль Оригами) 2. <lora:2204898:1.0>, jima anime style, 3. <lora:2251286:0.9>, digital art 4. <lora:2212879:1.0>, VectorPaintDaal, 5. <lora:2167278:1.0>,anime, illustration, 6. <lora:2172645:1.0>, Minimalist flat vector art; flat colors; no lineart; simple shapes; soft, subtle gradients; 💙Neuro…
👍12❤1
#lora@neurochan_tricks #стиль@neurochan_tricks #Flux1Krea Стили на Krea! 1. <lora:2059239:0.8>, ACMS1, photograph, sunlight, (стиль будто фото на фотоаппарат) 2. <lora:1428894:1.0>, m9rc3, 3. <lora:2242414:1.0>, grimmsfantasy, realistic painting, 4. <lora:2098757:1.0>, A painting by HOPEGANG, 5. <lora:2196476:1.0>, Retro Anime, 6. <lora:2248243:1.0>, watercolor, Elyrien style artwork, abstract, 💙Neurochan Ai
👍12👎2
Showing the 10 most recent of 10 posts we hold for @neurochan_tricks. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
Republishes
Channels on the register whose posts this channel has forwarded.
Built only from forwarded posts we have actually read, on both sides. Coverage is early and deliberately incomplete: a missing link means we have not read the post that would prove it, never that the relationship does not exist. Counts are distinct forwarded posts observed, so they only ever go up as we read more.
Named by 1 registered channel — every channel on the register whose own posts have named this one, by its current username or any other username it currently holds, merged from two separately captured readings of the same fact so a namer caught by only one of them is not missed and a namer both caught is not counted twice. A username this channel has since dropped is not matched — that handle may belong to someone else now, and crediting today’s namer to yesterday’s owner would misattribute it.
Named by
Channels on the register whose posts name this channel's handle.
A mention is a weaker signal than a forward and is counted separately for that reason — naming a channel is not republishing it, and a handle in a post body is easy to place deliberately. The post counts beside each row below are distinct posts in which the handle appeared, from posts we have read on both sides — the “Named by N registered channels” figure above is a different count, of distinct NAMING CHANNELS rather than posts, and is not the sum of the rows under it.
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 5 September 2026 — this entry's latest reading, not the date you are reading this.
“Neurochan AI [Второй канал]” (@neurochan_tricks), 883 subscribers as measured 5 September 2026. Telegram Register, tgregister.com/channel/neurochan_tricks.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.