Home / Blog
Guides on training, prompting and running open models locally. Every claim is traced to a primary source — official docs, model cards, repositories, or the code itself.
AI video (4)Training LoRAs (7)Models of 2026 (5)ComfyUI (2)Prompting and control (3)Fixing things (4)
How to configure Anima for image generation, pick the right sampler, and train a LoRA locally with verified settings and hyperparamete…
Choose the right cloud GPU instance, compare templates, and keep costs low.
A practical guide to sourcing images, cleaning data, and using JoyCaption and WD14 tagger for LoRA training dataset preparation.
A guide to running FLUX.2 Klein 9B locally, using consistency LoRAs for character work, and comparing it with Flux.1-dev
Forge, SwarmUI, and SD.Next as A1111 replacements — what breaks, what survives, extension migration guide.
Pick the right HunyuanVideo model file for your GPU, configure ComfyUI, and train a video LoRA.
Which anime characters Illustrious XL and NoobAI know natively, how to prompt them with Danbooru tags, and practical LoRA training set…
Verified KREA 2 Turbo photorealism settings, prompt framing for zoom control, and 2026 model comparisons.
A practical methodology for fair Stable Diffusion model comparisons — control variables and read grids honestly.
When to use Textual Inversion over LoRA, Kohya_ss and A1111 settings, and the learning-rate gap explained.
Compare latent upscaling, model upscalers, hires fix, and tiled workflows. Learn which method works best for photorealistic vs illustr…
Compare five acceleration techniques for ComfyUI video workflows — benchmarks, trade-offs, and install steps for each method.
Learn to run Z-Image Turbo locally, build img2img and inpainting workflows in ComfyUI, and train character LoRAs with the ostris train…
Camera angle and shot-type vocabulary for Stable Diffusion and SDXL prompts, with verified resolution, CFG, sampler and weighting sett…
FLUX.1 LoRA training parameters explained: dataset prep, captioning, learning rate, network dim and alpha, and VRAM for 12GB–24GB GPUs.
Which conditioning tool to use in ComfyUI for style transfer, composition and character consistency — and the settings that work.
Merge Stable Diffusion checkpoints: weighted sum vs add difference, SDXL block weights, merge vs LoRA, and how to evaluate the result.
Negative prompts work on SD 1.5 and SDXL but do nothing on Flux dev, SDXL-Turbo and Pony by default. See what steers each model family.
What score_9, score_8_up, source_pony, and rating_safe do in Pony Diffusion, how Illustrious masterpiece tags differ, and when quality…
Resolve ComfyUI import failures, onnxruntime-gpu CUDA mismatches, and embedded Python package location issues with verified fixes.
Compare ADetailer for A1111/Forge and FaceDetailer for ComfyUI — automatic inpainting that detects faces, hands, and persons.
Pick the right sampler for SD1.5, SDXL, and Flux — deterministic vs. stochastic, step count trade-offs, and scheduler settings that ma…
Free LoRA training guide: dataset prep, WD14/BLIP captioning, and the hyperparameters that actually matter. Colab + local workflows.
Fix CUDA OOM with PYTORCH_CUDA_ALLOC_CONF, optimize FLUX training with blocks_to_swap, and run Wan2.1 and HunyuanVideo on 12 GB GPUs.
Sequential ComfyUI chain: high-noise KSampler feeds low-noise KSampler. Correct LoraLoaderModelOnly setup and training guide.