…Download
0410

ToshLLM field guide

Image and video studio

Generate, upscale and queue images, create local video, and manage models and VRAM across AMD GPUs.

Verified against the appUpdated August 16, 2026Practical reference
Creative modes

Use the same Mac for three local workflows.

The segmented control above the main window switches between Chat, Images and Video. Each studio has its own model catalog and runtime. Loading a language model is not required for image or video generation.

Create imagesText to image and image to image through the bundled stable-diffusion.cpp runtime.
UpscaleProcess one or more existing images with ESRGAN models at 2x or 4x.
QueuePrepare several prompts and dispatch them to available image instances without overlapping work on one GPU.
Create videoGenerate a local frame sequence from text or, on supported models, an initial image.
Image models

Let VRAM guide the first choice.

The catalog ranges from compact Stable Diffusion models to Z-Image, Flux and Qwen-Image variants. ToshLLM recommends a model from the selected GPU's usable memory and downloads every required component, including diffusion weights, VAE and text encoders.

Model licenses differ. The catalog labels large or restricted models, but you remain responsible for checking the upstream model license before commercial use or redistribution.

Download size and resident VRAM are different.

A model can contain several components that load at different stages. ToshLLM estimates the component that remains resident during sampling and accounts for transient encoders and VAE work separately.

Image controls

Change one visual variable at a time.

  • Aspect and size: available dimensions follow the model's latent grid, quality limits and detected VRAM.
  • Steps: distilled and Turbo models expect few steps, while other models need a longer sampling run.
  • CFG: use the model's recommended guidance before experimenting.
  • Seed: keep a fixed value to compare prompt or setting changes; use -1 for a new result.
  • Image to image: a lower strength preserves more of the reference and a higher value reinvents it.
  • Output: PNG preserves lossless output; JPG is smaller for photographic results.

A mismatch between the reference image and output aspect ratio can crop or distort the composition. Match both ratios before judging the model.

Parallel GPUs

Separate work without competing for one card.

You can add image-generation instances with their own model, GPU and settings. The prompt queue assigns work only to idle instances and avoids starting two queued jobs on the same GPU.

An instance can also place the main diffusion model on one GPU and supporting components on another. CPU offload reduces VRAM pressure by moving components through system memory, with a speed cost.

Avoid two active instances on one AMD GPU.

The app warns about this configuration because simultaneous heavy Metal workloads can exhaust memory or destabilize the card.

Upscaling

Compare the source and result directly.

The Upscale view accepts batches and processes them one at a time. ToshLLM can download the curated ESRGAN model or use a compatible custom model. A 4x model produces native 4x output; the 2x option scales with the same model and resamples to half.

Results are stored beside the source by default and the comparison view keeps the original available for inspection. Upscaling adds pixels and detail, but it cannot reliably restore information absent from the source.

Video generation

Budget memory across space and time.

The video catalog includes text-to-video and image-to-video models. Select a frame size, a valid frame count, steps, seed and GPU. The memory estimate accounts for resolution, number of frames and resident model size.

If a run approaches the memory limit, reduce frame count first, then resolution. The studio keeps generated frames as individual PNG files and previews them as an animation.

Text to videoCreates the sequence from the written prompt alone.
Image to videoUses the selected image as the first frame when the model supports it.
PreviewPlay the frame sequence or pause and scrub individual frames.
ExportUses ffmpeg to encode an H.264 MP4 that macOS can play directly.

MP4 export and video attachments require ffmpeg and ffprobe. ToshLLM searches its bundled tools and common local installation paths.