FreakyJolly: AI Tutorials, ComfyUI Workflows and Local AI Guides
ComfyUI API Guide: Run Workflows From Python (Prompt, WebSocket, Images)
LM Studio Not Loading Models? How to Fix “Failed to Load Model” and Search Errors
ComfyUI Inpainting Not Working? Every Cause and Fix (SD, SDXL and Flux Fill)
Seedream 5.5 Guide: 100-Round Editing, Transparent PNGs, Pricing and How to Use It (2026)
Claude Fable 5.2 and Mythos 5.2: Price, Benchmarks, Plan Access and How to Use Them (2026)
SnapRef V2A for Anima in ComfyUI: Same Character in Every Scene
The world of AI. Explained.
A clearer view of artificial intelligence.
Hands-on guides for ComfyUI workflows, AI video, image editing and running models locally — tested, with every file path and setting written down.
- Lead story
ComfyUI API Guide: Run Workflows From Python (Prompt, WebSocket, Images)
Run ComfyUI workflows from Python: export API format, queue with /prompt, change prompts and seeds, wait over WebSocket, download images and batch runs.
The reading list
Latest stories
LM Studio Not Loading Models? How to Fix “Failed to Load Model” and Search Errors
Fix LM Studio failed to load model, missing models and broken search: read the log, memory settings, runtimes, folder layout, files and…
ComfyUI Inpainting Not Working? Every Cause and Fix (SD, SDXL and Flux Fill)
Fix ComfyUI inpainting that returns the same image, a grey patch, seams or blur: the right encode node, denoise values, masks and…
MiniMax H3 Max Editing Nodes in ComfyUI: Recast, Extend, Reframe, Insert, Lip Sync and Camera Control
All six MiniMax H3 Max editing nodes in ComfyUI explained: what each does, exact limits, reported prices, setup, workflows and fixes.
Seedream 5.5 Guide: 100-Round Editing, Transparent PNGs, Pricing and How to Use It (2026)
ByteDance’s Seedream 5.5 (9 Nov 2026) promises 100 stable edit rounds and native transparent PNGs from $0.02 an image. Where to use…
Claude Fable 5.2 and Mythos 5.2: Price, Benchmarks, Plan Access and How to Use Them (2026)
Anthropic’s Claude Fable 5.2 and Mythos 5.2 launched 9 Nov 2026 at $8/$40 per million tokens. Full benchmarks, the Fermat result, plan…
FLUX.1 Kontext Dev in ComfyUI: Complete Image Editing Guide
Edit images with words using FLUX.1 Kontext Dev in ComfyUI: exact files and folders, the node chain, settings, prompt rules, multi-image, GGUF…
SnapRef V2A for Anima in ComfyUI: Same Character in Every Scene
How to install and use SnapRef V2A with Anima in ComfyUI: files, folders, the SnapRef node, cs and char modes, settings, workflows…
Open H3 Regenerate 2K IC in ComfyUI: Sharper MiniMax H3 Video That Keeps Faces
Set up the Open H3 Regenerate 2K IC LoRA in ComfyUI: node pack, exact model folders, LoRA order, up3/up4/hf8 modes, VRAM limits…
WeVisOne-VL in ComfyUI: Cut Out, Detect and Read Anything From One Prompt
Tencent’s WeVisOne-VL now runs natively in ComfyUI. Files, folders, the one-node setup, every task mode, a cutout workflow and fixes.
How every guide is built
Copy the command. Drop the file. Run the graph.
Each ComfyUI guide follows the same shape, so you can skim straight to what you need.
- Step 1InstallNode packs and exact download commands.
- Step 2Files & pathsEvery model folder in one table.
- Step 3SettingsStarting values that work on consumer GPUs.
- Step 4TroubleshootKnown errors and the fix for each.
New models land fast. Get the working setup first.
Follow FreakyJolly in any feed reader to get every new guide the moment it goes live.