https://youtu.be/5700Hao79d8?si=H2cxZhgjPHAtxAcg

Channel
ComfyUI (Flux, ZIT, QWEN)
@AI_SD
On this record: Topic · Growth · Engagement · Reactions · Posts · Citations · Telegram's recommendations · Cite this entry
4,308subscribers
+64 since we began measuring on 7 August 2026
Risers and fallers across the register · movement among entries of 3,162–10,000.
Register entry
| Telegram ID | -1001812045716 |
|---|---|
| Type | Channel |
| Username | @AI_SD |
| Created | Between 1 October 2022 and 30 September 2023 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 7 August 2026 |
| Last confirmed live | 26 September 2026 |
| Measurements held | 15 |
| Confirmed unchanged | 1 time, most recently 26 September 2026 |
| On Telegram | t.me/AI_SD |
Topic
Technology — a classification, not a measurement. An on-box language model (Qwen3.6-35B-A3B-FP8, prompt version 1) read this channel’s own recent posts on 13 September 2026 and assigned it the closest of 31 fixed categories, at 78% confidence. This is a model’s judgement about what the channel is likely to be about, not a fact this register measured the way a subscriber count or a view count is measured — it can be revised on a later pass, and it carries no weight anywhere else on this page. How this classification works, and why it has no browse page of its own yet.
Growth
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 26 Sept 2026, 03:17 | 4,308 | +11 |
| 15 Sept 2026, 20:57 | 4,297 | +13 |
| 11 Sept 2026, 19:15 | 4,284 | -1 |
| 7 Sept 2026, 08:16 | 4,285 | +3 |
| 2 Sept 2026, 05:28 | 4,282 | +3 |
| 30 Aug 2026, 15:57 | 4,279 | -10 |
| 25 Aug 2026, 03:11 | 4,289 | +5 |
| 21 Aug 2026, 23:18 | 4,284 | +17 |
| 19 Aug 2026, 04:37 | 4,267 | +10 |
| 16 Aug 2026, 05:36 | 4,257 | +5 |
| 13 Aug 2026, 00:49 | 4,252 | +3 |
| 10 Aug 2026, 10:40 | 4,249 | +3 |
| 7 Aug 2026, 14:52 | 4,246 | +2 |
| 7 Aug 2026, 09:31 | 4,244 | no change |
| 7 Aug 2026, 09:29 | 4,244 | first reading |
Engagement
6 posts held, back to 18 July 2026 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 5 pages 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 6 posts for this entry, the most recent from 31 July 2026. An engagement rate over an empty window would be a number about nothing.
Reaction mix
12 reactions across 3 posts, in 4 distinct kinds. The most used accounts for 58.3% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| ❤ | 7 | 58.3% | |
| 🔥 | 2 | 16.7% | |
| 🤝 | 2 | 16.7% | |
| ⚡ | 1 | 8.33% |
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 3 of the 6 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 12 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 6 most recent posts we hold, published 18 July 2026 to 31 July 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.
Recent posts
https://youtu.be/Pz3qs7puY08?si=QHwJFM777WIYJbD3 Хороший пример с юмором, показывающий на каком этапе сейчас находится разработка игр с использованием вайбкодинга.
Тестовая модель нейронки от компании OpenAI вышла из-под контроля и устроила кибератаку Компания OpenAI, создатель чатбота ChatGPT, признала, что её новый ИИ‑агент во время внутреннего тестирования безопасности вышел из‑под контроля и сумел взломать систему стороннего стартапа. В опубликованном во вторник заявлении OpenAI сообщила, что на прошлой неделе, в ходе проверки в контролируемой среде, автономный агент — пр…
У меня дома есть цветной фото-принтер и, время от времени, я распечатываю генерации, но на всех них присутствую я. Необычный пейзаж сперва генерирую отдельно, а себя подставляю при помощи Flux Klein. Для примера я поставил Леонардо, и для быстрого результата я делал это на 4 шагах. Но если повысить cfg с 1 до 4 и количество шагов с 4 до 20, то результат будет более качественным. (Мой компьютер слишком слаб для этого)…
❤1
Интересную вещь узнал. Для снижения размытия в генерациях FLUX и ZIT, нужно использовать специальный VAE декодер - Ultra Flux 4K VAE . Скачиваете по этой ссылке файл diffusion_pytorch_model.safetensors затем переименовывайте его Ultra Flux 4K VAE.safetensors чтобы самому в будущем не запутаться. Промпт у этой картинки Realistic Photography Modern city, buildings with white walls and huge oval windows, lake scene at …
❤6⚡1🤝1
Решил сделать очередную партию декстопных обоев. Обычно я их делаю во Flux Schnell, там природа невероятно превосходная получается. В этот раз я решил посмотреть, что обновилось в ZIT. Первые тесты показали весьма «бедные» результаты в плане композиции. Пошёл смотреть, что есть на civitai и обнаружил вот такую лору. Триггер на её включение Realistic Photography который надо вставлять в начале промпта. Желательно прид…
🔥2🤝1
Showing the 6 most recent of 6 posts we hold for @AI_SD. 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.
Mentions
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.
Appears in Telegram’s recommendations for other channels
The reverse of the list above, and a different kind of signal. This does not require this channel to have ever been asked about directly — each row below is a channel we DID ask Telegram about, whose Telegram-generated list happened to include this one. A channel can appear here with an empty list above it, because being named by someone else’s query is independent of having been queried itself.
@neuro_artss · 26,430
Telegram ranks this channel #30 of 45 here — alongside 44 others — read 12 September 2026
@neyr0graph · 34,431
Telegram ranks this channel #48 of 90 here — alongside 89 others — read 3 September 2026
@yes_ai_official · 98,596
Telegram ranks this channel #54 of 83 here — alongside 82 others — read 22 August 2026
@neuralpony · 195,187
Telegram ranks this channel #55 of 61 here — alongside 60 others — read 13 August 2026
@StableDiffusionBest · 32,596
Telegram ranks this channel #58 of 84 here — alongside 83 others — read 4 September 2026
@mdj_school · 24,649
Telegram ranks this channel #68 of 88 here — alongside 87 others — read 15 September 2026
@MidJourneyAI1 · 33,710
Telegram ranks this channel #68 of 82 here — alongside 81 others — read 4 September 2026
@dailyprompts · 42,650
Telegram ranks this channel #71 of 91 here — alongside 90 others — read 29 August 2026
@digital_midjourney · 29,307
Telegram ranks this channel #76 of 81 here — alongside 80 others — read 8 September 2026
@prompty · 60
Telegram ranks this channel #79 of 89 here — alongside 88 others — read 7 September 2026
@neurogen_news · 22,946
Telegram ranks this channel #81 of 88 here — alongside 87 others — read 19 September 2026
@aiaiai · 176,423
Telegram ranks this channel #90 of 93 here — alongside 92 others — read 12 August 2026
@tips_ai · 25,359
Telegram ranks this channel #95 of 95 here — alongside 94 others — read 14 September 2026
@NeuralProfit · 23,415
Telegram ranks this channel #96 of 96 here — alongside 95 others — read 18 September 2026
@prompt_design · 86,986
Telegram ranks this channel #96 of 96 here — alongside 95 others — read 18 August 2026
This channel appears in 15 seed channels' Telegram-generated recommendation lists in total. Each is Telegram’s list for THAT channel, not this one — see how this is measured.
Cite this entry
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 26 September 2026 — this entry's latest reading, not the date you are reading this.
“ComfyUI (Flux, ZIT, QWEN)” (@AI_SD), 4,308 subscribers as measured 26 September 2026. Telegram Register, tgregister.com/channel/AI_SD.
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.