Channel
@casual_gan
On this record: Topic · Growth · Engagement · What this channel posts · Reactions · Posts · Cite this entry
944subscribers
-19 since we began measuring on 7 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
| Telegram ID | -1001162531650 |
|---|---|
| Type | Channel |
| Username | @casual_gan |
| Created | Between 1 March 2018 and 31 July 2021 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 8 August 2026 |
| Last confirmed live | 24 October 2026 |
| Measurements held | 11 |
| Confirmed unchanged | 1 time, most recently 24 October 2026 |
| On Telegram | t.me/casual_gan |
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 19 September 2026 and assigned it the closest of 31 fixed categories, at 95% 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 the other topics.
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 24 Oct 2026, 20:55 | 944 | -1 |
| 18 Oct 2026, 01:57 | 945 | -2 |
| 10 Oct 2026, 08:57 | 947 | -2 |
| 29 Sept 2026, 12:16 | 949 | -2 |
| 15 Sept 2026, 07:54 | 951 | -1 |
| 8 Sept 2026, 11:55 | 952 | -3 |
| 29 Aug 2026, 11:17 | 955 | -1 |
| 22 Aug 2026, 12:56 | 956 | -4 |
| 14 Aug 2026, 21:16 | 960 | -3 |
| 8 Aug 2026, 00:47 | 963 | no change |
| 7 Aug 2026, 20:33 | 963 | first reading |
20 posts held, back to 5 April 2022 — 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 20 posts for this entry, the most recent from 3 February 2024. An engagement rate over an empty window would be a number about nothing.
Measured directly from 1 video with a duration reading, out of the posts we hold for this channel — not this channel’s whole posting history, only the sample this register has actually read. An exact reading to the second, taken from the post itself rather than from Telegram’s own rounded chrome, so it carries no ≈ mark.
169 reactions across 20 posts, in 4 distinct kinds. The most used accounts for 62.7% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 🔥 | 106 | 62.7% | |
| 👍 | 36 | 21.3% | |
| ❤ | 26 | 15.4% | |
| 🤩 | 1 | 0.592% |
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 20 of the 20 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 169 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 20 most recent posts we hold, published 5 April 2022 to 3 February 2024, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.
Hi everyone! I hope this message finds you well! Wow, it has been a while since my last post here 😅 I am doing alright, no worries. This is actually a "Good News" post. I tried building some GPTs on the new OpenAI store and realized that they don't have even the most basic analytics to measure engagement with your creations, which is frustrating if you want to grow your GPTs. ✨Here is the good news: My buddy and …
🔥19❤6👍1🤩1
#87: "Hierarchical Text-Conditional Image Generation with CLIP Latents" by Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu et al. explained in 5 minutes As always, here is the visual summary! (All figures are taken from the original paper) *** Tip Casual GAN Papers on KoFi to help this community grow!
❤14👍4🔥1
#87: "Hierarchical Text-Conditional Image Generation with CLIP Latents" by Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu et al. explained in 5 minutes Does this paper even need an introduction? This is DALL-E 2 and if you have somehow not heard of it yet, sit down. Your mind is about to be blown. Enough said. Let’s dive in, shall we? https://www.casualganpapers.com/sota-text-to-image-openai-clip-dalle/D…
🔥7👍1
Hey everyone, It has been a while! I was busy with a NeurIPS submission 👀 but I think I am back now. Lots of papers to cover, lots of posts to write, lots of people to meet! Let's start this off with a bang that is DALL-E 2 💥 Surprisingly well written, less wordy than StyleGAN 3, and an elegant idea as long as you pretend that the diffusion math doesn't exist 🤡 Best, -Kirill
🔥10👍1
#86.4: "High-Resolution Image Synthesis with Latent Diffusion Models” by Robin Rombach, Andreas Blattmann et al. As always, here is the visual summary! (All figures are taken from the original paper) *** Tip Casual GAN Papers on KoFi to help this community grow!
🔥5
#86.0: "High-Resolution Image Synthesis with Latent Diffusion Models” by Robin Rombach, Andreas Blattmann et al. Hi everyone! We are almost all caught up with diffusion and text-to-image goodness! Best, -Kirill
🔥5👍1
#86.1: "High-Resolution Image Synthesis with Latent Diffusion Models” by Robin Rombach, Andreas Blattmann et al. 🔑 Keywords: #faster_diffusion_models #no_CLIP_reranking #classifier_free_guidance 🎯 At a glance: One of the cleanest pitches for a paper I have seen: diffusion models are way too expensive to train in terms of memory, time and compute, therefore let’s make them lighter, faster, and cheaper. As for the d…
🔥6❤1
#86.2: "High-Resolution Image Synthesis with Latent Diffusion Models” by Robin Rombach, Andreas Blattmann et al. Continued from the message above ☝️ 🔍 Main Ideas: 1. Perceptual Image Compression: Authors train an autoencoder that outputs a tensor of latent codes. This latent embedding is regularized with vector quantization within the decoder. This is a slight but important change from VGQAN that means the underly…
🔥5
#86.3: "High-Resolution Image Synthesis with Latent Diffusion Models” by Robin Rombach, Andreas Blattmann et al. Continued from the message above☝️ 📈Experiment insights / Key takeaways: - Baselines: LSGM, ADM, StyleGAN, ProjectedGAN, DC-VAE - Datasets: ImageNet, CelebA-HQ, LSUN-Churches, LSUN-Bedrooms, MS-COCO - Metrics: FID, Perception-Recall - Qualitative: x4-x8 compression is the sweet point for ImageNet - Quant…
🔥5👍1
#85.4: "GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models” by Alex Nichol et al. As always, here is the visual summary! (All figures are taken from the original paper) *** Tip Casual GAN Papers on KoFi to help this community grow!
👍2🔥2
#85.1: "GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models” by Alex Nichol et al. 🔑 Keywords: #faster_diffusion_models #no_CLIP_reranking #classifier_free_guidance 🎯 At a glance: “Diffusion models beat GANs”. While true, the statement comes with several ifs and buts, not to say that the math behind diffusion models is not for the faint of heart. Alas, GLIDE, an OpenAI paper…
🔥4
#85.2: "GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models” by Alex Nichol et al. Continued from the message above ☝️ 🔍 Main Ideas: 1. Model: The authors take the ADM (the standard diffusion model) architecture and extend it with text conditioning information. This is done by passing the caption through a transformer model and using the encoded vector in place of the class…
🔥3
Showing the 12 most recent of 20 posts we hold for @casual_gan. 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.
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 24 October 2026 — this entry's latest reading, not the date you are reading this.
“Casual GAN Papers” (@casual_gan), 944 subscribers as measured 24 October 2026. Telegram Register, tgregister.com/channel/casual_gan.
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.