JasonHoku-ComfyUI-Ultimate-Auto-Sampler-Config-Grid-Testing-Suite/examples

Example workflows

One ready-to-run workflow per model family. Each file is the same three-node graph (Config Builder -> Sampler Grid -> Grid Dashboard) with the Builder already filled in for that model: model, text encoder, CLIP type, VAE, sampler/scheduler/steps/cfg axes and a prompt.

How to load one

1. Download the model files listed for the example and put each in the folder shown (under ComfyUI/models/). The official Comfy-Org workflow templates and Hugging Face repos for each family ship exactly these files.
2. Drag the .json onto the ComfyUI canvas.
3. Open the Config Builder. If your file names differ, pick yours in the model / text encoder / VAE dropdowns. A file you do not have is shown as missing rather than silently replaced.
4. Queue the prompt. Results appear in the Dashboard node.

Times are approximate on an RTX 5060 Ti 16 GB, not counting the first model load.

SDXL / Illustrious (uscg-sdxl-illustrious.json)

File	Folder
sd_xl_base_1.0.safetensors	models/checkpoints/

• What the grid tests: 2 samplers (dpmpp_2m, euler) x 2 schedulers (karras, normal) x cfg 5 and 7 x 2 prompts at 25 steps, 1024x1024. 16 images
• Time: TBD
• Notes: the checkpoint has the VAE and CLIP built in, so no extra files. Swap in any Illustrious/SDXL checkpoint.

Anima (uscg-anima.json)

File	Folder
anima-base-v1.0.safetensors	models/diffusion_models/
qwen_3_06b_base.safetensors	models/text_encoders/
qwen_image_vae.safetensors	models/vae/

• What the grid tests: 2 samplers (er_sde, euler) x simple scheduler x cfg 4 and 5 at 30 steps, 1024x1024. 4 images
• Time: TBD
• Notes: the CLIP type stays stable_diffusion; there is no separate Anima option and ComfyUI picks the Anima text encoder from the Qwen3-0.6B file.

Z-Image Turbo (uscg-z-image-turbo.json)

File	Folder
z_image_turbo_bf16.safetensors	models/diffusion_models/
qwen_3_4b.safetensors	models/text_encoders/
ae.safetensors	models/vae/

• What the grid tests: res_multistep / simple at 8 and 10 steps, cfg 1, 1024x1024. 2 images
• Time: TBD
• Notes: CLIP type lumina2. Model Sampling is set to AuraFlow with shift 3, as in the official template.

Krea 2 Turbo (uscg-krea2-turbo.json)

File	Folder
krea2_turbo_fp8_scaled.safetensors	models/diffusion_models/
qwen3vl_4b_fp8_scaled.safetensors	models/text_encoders/
qwen_image_vae.safetensors	models/vae/

• What the grid tests: euler / simple at 6 and 8 steps, cfg 1, 1024x1024. 2 images
• Time: TBD
• Notes: CLIP type krea2.

Flux.2 Klein 9B (uscg-flux2-klein-9b.json)

File	Folder
flux-2-klein-9b-fp8.safetensors	models/diffusion_models/
qwen_3_8b_fp8mixed.safetensors	models/text_encoders/
flux2-vae.safetensors	models/vae/

• What the grid tests: euler at 4 and 6 steps, 1024x1024, each with the Advanced Sampling pipeline (CFG guider + Flux2 scheduler) and without it (plain KSampler, simple scheduler): the Builder always grids Advanced Sampling on vs off. 4 images
• Time: TBD
• Notes: Klein is distilled, so cfg is 1; the official (distilled) template uses the CFG guider plus the Flux2 scheduler, which is the Advanced Sampling half of the grid. CLIP type flux2.
• Base variant: this example uses the distilled checkpoint. For the base model use flux-2-klein-base-9b-fp8.safetensors (same folder) with ~20 steps and cfg 5 (CFG guider + Flux2 scheduler), as in Comfy's image_flux2_klein_image_edit_9b_base template.

MOSS-Image (uscg-moss-image.json)

File	Folder
moss_image_sft_int8_convrot.safetensors	models/diffusion_models/
qwen3.5_9b_w4a8_gptq.safetensors	models/text_encoders/
flux2-vae.safetensors	models/vae/

• What the grid tests: two config arrays with the same prompt and settings (er_sde / simple, 25 steps, cfg 2.5): one with Skip Layer Guidance on, one off. 2 images
• Time: TBD
• Notes: SLG uses the official recipe, single block 22 for the first 0-50 % of the steps. Compare the two images to see what it does. CLIP type moss_image. A smaller flux2-vae_small.safetensors VAE also exists and can be picked in the Builder instead. The 9B text encoder is large; on a 16 GB card expect model swapping.

Workflow Sweep on your own graph (uscg-workflow-sweep-sdxl.json)

File	Folder
sd_xl_base_1.0.safetensors	models/checkpoints/

• What the grid tests: one Workflow Sweep array that wraps a complete SDXL text-to-image graph (Load Checkpoint, two CLIP Text Encode, Empty Latent 1024x1024, KSampler, VAE Decode, Save Image) and sweeps three things on it: KSampler cfg 5 and 7 x sampler_name euler and dpmpp_2m x 2 positive prompts (one shared negative). 8 images
• Time: TBD
• Notes: unlike the other examples, the Builder does not build the pipeline here. The sweep runs your exact exported graph once per job, changing only the inputs you bound, and collects the result into the Dashboard like any other run. This is how to grid-test a workflow the three-node grid cannot express, such as reference-image conditioning, ControlNet, multi-stage or custom-node graphs. To use your own: in ComfyUI use Export (API), open the Config Builder's Workflow Sweep section, load that file, pick the output image, and choose the inputs to sweep. Any API-format export works, for example the Flux.2 example in this folder could be exported and swept the same way. The embedded SDXL graph here is only a stand-in so the example runs with one checkpoint.

Make your own

• Edit the Builder: add LoRAs or a whole LoRA folder, more samplers, schedulers, step counts, cfg values, resolutions or prompts. Every list is multiplied together.
• Raise Additional Random Seeds in Run Settings to render extra seeds per config, handy for telling what the model does from what a LoRA does.
• Add another config array to compare models or settings side by side (the MOSS example does this for SLG).