I tested Qwen 3.8 vs Fable 5 Both were... made with Renoise CLI. Which output do you like better? Prompt in thread 🧵show more

AI agents can do animation for you now. All... I did was create the character in GPT Image 2.0. Fable 5 handled the story and prompt, then I used Renoise CLI to run it with Seedance 2.0. Prompt in thread ⤵️show more

Qwen 3.8 vs Fable 5 Created with Arcads

I tested again Gemini 3.7 Flash vs Qwen 3.8... vs Grok 4.6 vs GLM 5.3 same prompt: a family having lunch in 3D. Qwen 3.8 wins again for me on quality. but Gemini finished in under 2 mins, the others took 6+. Which one wins for you?show more

I tested Gemini 3.7 Flash vs Qwen 3.8 vs... DeepSeek V4 Pro vs GLM 5.3 same prompt: a busy train interior, then leaving the station. Qwen 3.8 and GLM 5.3 look best to me. but Gemini did it in 1 min 45 secs lol, others took more than 7 mins. Which one wins for you?show more

GPT-6 Astra vs. Fable 5.1 both made using same... prompt & /goal (fable did sky theme and astra did astro theme) which one did it better?show more

DeepSeek V4 Flash vs GPT-5.6 Luna tested both models... with the same prompt on highest reasoning > luna one shotted everything in under 3 mins in devin > v4 Flash needed an extra prompt to fix the movement and took over 5 mins in aihubmix cli which one do you think won?show more

Kimi K3 VS Claude Fable 5. Prompt in the... 🧵, now try it on Flowith.show more

This is literally my new workflow now: Character Design... → GPT Image 2.0 Story & Prompt → Fable 5 Animation → Seedance 2.0 Prompt in thread 🧵show more

Another comparison round. Seedream 5.0 Pro vs. GPT Image... 2.0, both animated with Seedance 2.0. Prompt in the thread 🧵show more

Seedream 5.0 Pro vs. GPT Image 2.0. Both animated... in Seedance 2.0. Prompt in the thread 🧵show more

Qwen 3.8 27b nvfp4 vs Grok 4.6 Someone tell... me how this local model that is 100x smaller and 10x slower made a better animation?! Elon Musk help us solve this, both with their highest thinking mode (xhigh vs max)show more

GPT 5.6 Pro Mogs Fable 5 in this prompt... 😳 Prompt : make bmpt-72 turret in three js - low poly with recognizable silhuette in one html code block . quoted image is output from fable 5 created by Mirochillshow more

Fable 5.1 vs Kimi K3 Tested both models with... the same prompt at the highest reasoning level available. > Fable took 18 minutes to complete this test and cost $12.60 > Kimi K3 took 10 minutes and cost around $6.95 Which one wins here?show more

Seedream 5.0 Pro vs. GPT Image 2.0. Both were... animated with Seedance 2.0. Check replies to find the prompt 🧵show more

Fable 5.1 vs GPT 5.6 Sol tested both models... with same prompt at highest reasoning available > Fable took 10 minutes to complete this test and costed $1.6 > Sol took 7 minutes and costed around $.95 even tho sol is cheaper and faster but results are really different which one won here?show more

GPT 5.6 Sol vs. Fable 5 in action-figure animation,... both generated with Seedance 2.0.show more

Qwen 3.8 Flash Next (125B A6B MoE) Vs Qwen... 3.8 27B (dense) - Both Q4_K_XL - Reasoning Off Prompt: Create a very high quality realistic video like animation of the solar system. three.js via cdn. Let the camera revolve around. single html file. dont call any tools. dont need any controls. Qwen 3.8 27b focused on computational physics & geometry (inclinations, coordinate math, moon orbits). While Qwen 3.8 125B A6B focused on cinematography & visual UX (lighting contrast, atmospheric glow, framing, and HUD overlays). It also followed the camera instruction correctly and produced result thats visually more stunning. Both the models run on single RTX 3090/4090 (24 GB VRAM). the 27b will fit entirely in the VRAM, but you'd need 100-120GB RAM for the new 125B MoE (check out the previous post for complete inference benchmarks and llama.cpp setup) Qwen 3.8 Flash Next beats Qwen 3.8 27B in almost all the benchmarks. have dropped the intelligence benchmark comparison and unsloth quant huggingface links in the replies. Which one would u be running regularly on your hardware?show more

Yup! Gemini 3.8 Flash made this in Antigravity.. It's... exceptionally good in frontend tasks.. i was amazed to see this level of polished output.. It did take a few iterations to tweak specific animations and morphing but this result is unreal! Which one do you like more?show more

🚨 Qwen new checkpoint - kieran As usual it... claims he is claude and made by anthropic but with tokenizer prompt , its clear - QWEN model Ignore website this is my test to know which model is which behind the scene , should i test it and compare with kimi k3 / opus 5 /sol 5.6show more

Okay, I am fairly confident in my hypothesis now.... The secret sauce behind Qwen 3.8 27B becomes almost immediately evident during testing. It is not the training data. In fact, I doubt any SFT was involved at all. The model was simply allowed GRPO with a more liberal reasoning context length. As I have explained to you before, distillation through GRPO is powerful, and in certain contexts vastly superior to K/L divergence distillation. Qwen used the outputs of Qwen 3.8 Max as the reinforcement learning objective for Qwen 3.8 27B and told the model reason as much as it has to in order to match the output. Remember, Intelligence is solution, not compression. This is like nesting the output of a function as an additional input to itself, and it is absolutely brilliant.show more