
Image generation
ছবি বানানো AITurn a text prompt into 1024×1024 images with Stable Diffusion XL.
Open this notebook ↗Read the short write-up →Computer-vision pipelines parallelize naturally across AI Computers. The best accelerator depends on resolution, batch size, model architecture, training duration and whether the workload is training or inference.
Shared by the ComputeBD team. Open one, change it to fit your work, then run it on an AI Computer — billed by the minute.

Turn a text prompt into 1024×1024 images with Stable Diffusion XL.
Open this notebook ↗Read the short write-up →Teach Stable Diffusion XL the look of Dhaka rickshaw art with openly licensed pictures or your own photos.
Open this notebook ↗Read the short write-up →Fine-tune FLUX.1 [schnell] on Nakshi Kantha embroidery motifs and generate new designs from text.
Open this notebook ↗Read the short write-up →Learn Jamdani weaving geometry and create tileable, seamless textile patterns.
Open this notebook ↗Read the short write-up →
Generative AI, rendering, larger fine-tunes

Rendering, vision, medium training workloads

Fast inference, video AI, efficient fine-tuning

LLM fine-tuning, research, high-throughput training
Tell us your workload and preferred AI Computer.
Join waitlist ↗Memory (VRAM) needed for Llama, Qwen, Mistral, Stable Diffusion, FLUX… — which AI Computer fits, and the cost per hour in taka.
→“Open in ComputeBD” badgeA button for your GitHub README or notebook: one click opens the .ipynb on a ComputeBD AI Computer.
→AI glossary (Bangla)VRAM, fine-tuning, LoRA, RAG, tokens, quantization… explained in plain Bangla and English, one page per word.
→