FLUX.2 Dev Full (64GB) vs HiDream I1 Dev FP8 (Recommended)

Last data update: 2026-06-11T22:17:24.345Z

Intent: image-same-category-deployment-comparison

Quality gate

Eligible for indexable canary: yes
Evidence score: 7

Check	Pass	Evidence
same-type intent	yes	image vs image
distinct models	yes	flux2-dev vs hidream-i1-dev-fp8
pricing present	yes	$1.39/hr and $0.49/hr
deployment target present	yes	gpu-a100-80gb and gpu-a6000
source config facts present	yes	39 facts and 38 facts
same-type catalog context present	yes	27 image catalog rows
asset evidence when workflow model	yes	74 matched asset rows

Evidence summary

flux2-dev__hidream-i1-dev-fp8 intent: image-same-category-deployment-comparison; this pair is compared as a same-type deployment decision, not as an arbitrary generated adjacency;
flux2-dev__hidream-i1-dev-fp8 cost profile: flux2-dev costs $1.39/hr and $1000.8/mo at 720h; hidream-i1-dev-fp8 costs $0.49/hr and $352.8/mo at 720h;
flux2-dev__hidream-i1-dev-fp8 instance profile: flux2-dev=gpu-a100-80gb xlarge comfyui-flux2; hidream-i1-dev-fp8=gpu-a6000 large comfyui-hidream;
flux2-dev__hidream-i1-dev-fp8 description comparison: flux2-dev=Full 32B model; Requires 48GB+ VRAM (H100); Maximum quality and fidelity;; hidream-i1-dev-fp8=17B parameter model with excellent prompt following; Uses Flux architecture;
flux2-dev__hidream-i1-dev-fp8 group evidence: flux2-dev=FLUX.2 is Black Forest Labs' 32B parameter model with multi-image editing capabilities; The Dev FP8 variant runs on RTX 4090/5090, while the full model requires 48GB+ VRAM for maximum quality;; hidream-i1-dev-fp8=HiDream I1 is a 17B parameter image generation model with excellent prompt following; Available in Dev, Full, and Fast variants with FP8 quantization for efficient deployment on consumer GPUs;
flux2-dev__hidream-i1-dev-fp8 nearby catalog count: 27 image models were available for internal context during page selection;
flux2-dev__hidream-i1-dev-fp8 matched deployment assets: flux2_dev_fp8mixed.safetensors, hidream_i1_dev_fp8.safetensors, mistral_3_small_flux2_fp8.safetensors, flux2-dev-Q4_K_M.gguf, flux2-dev-Q5_K_M.gguf, flux2-dev-Q8_0.gguf, flux2-dev.safetensors, flux2-vae.safetensors;

	FLUX.2 Dev Full (64GB)	HiDream I1 Dev FP8 (Recommended)
Model group	flux2	hidream
Type	image	image
Source id	flux2-dev	hidream-i1-dev-fp8
Model size tier	xlarge	large
Deployment template	comfyui-flux2	comfyui-hidream
Docker image base	comfyui	comfyui
Container port	8188	8188
Web UI port	n/a	n/a
Volume mount path	/data	/data
Parameters	32B	17B
Context window	n/a	n/a
VRAM (GB)	80	48
Recommended GPU	gpu-a100-80gb	gpu-a6000
GPU type	NVIDIA A100 80GB PCIe	NVIDIA RTX A6000
GPU count	1	1
vCPU	8	9
RAM (GB)	117	50
Disk (GB)	300	200
Instance type	gpu-very-high-vram	gpu-high-vram-value
RunPod id	n/a	n/a
$/hr	$1.39	$0.49
$/month (24/7)	$1000.8	$352.8
Popularity (1-10)	8	8
Deploy time (min)	18	18

Cost delta /hr: $-0.9
VRAM delta GB: -32
Best GPU tier to fit both: gpu-a100-80gb

Cost scenarios

Usage level	Hours / month	flux2-dev	hidream-i1-dev-fp8	Delta
Prototype, 40 hr/mo	40	$55.6	$19.6	$-36
Part-time app, 160 hr/mo	160	$222.4	$78.4	$-144
Always-on, 720 hr/mo	720	$1000.8	$352.8	$-648

Decision matrix

Factor	flux2-dev	hidream-i1-dev-fp8	Winner
Lower hourly cost	$1.39/hr	$0.49/hr	hidream-i1-dev-fp8
Lower 24/7 monthly cost	$1000.8/mo	$352.8/mo	hidream-i1-dev-fp8
Lower VRAM tier	80GB	48GB	hidream-i1-dev-fp8
Higher popularity score	8/10	8/10	flux2-dev
Faster deployment estimate	18 min	18 min	flux2-dev
Template specificity	comfyui-flux2	comfyui-hidream	hidream-i1-dev-fp8

Pair config delta

flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__slug; flux2-dev=flux2-dev; hidream-i1-dev-fp8=hidream-i1-dev-fp8; comparison=different value; source=adapter identity
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__sourceId; flux2-dev=flux2-dev; hidream-i1-dev-fp8=hidream-i1-dev-fp8; comparison=different value; source=modelConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__displayName; flux2-dev=FLUX.2; hidream-i1-dev-fp8=HiDream I1; comparison=different value; source=modelConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__sizeVariant; flux2-dev=Dev Full (64GB); hidream-i1-dev-fp8=Dev FP8 (Recommended); comparison=different value; source=modelConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__modelGroup; flux2-dev=flux2; hidream-i1-dev-fp8=hidream; comparison=different value; source=modelConfig.js / modelSeoData.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__type; flux2-dev=image; hidream-i1-dev-fp8=image; comparison=same value; source=modelConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__modelSize; flux2-dev=xlarge; hidream-i1-dev-fp8=large; comparison=different value; source=resolved model config
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__templateName; flux2-dev=comfyui-flux2; hidream-i1-dev-fp8=comfyui-hidream; comparison=different value; source=resolved model config
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__dockerImageBaseName; flux2-dev=comfyui; hidream-i1-dev-fp8=comfyui; comparison=same value; source=resolved model config
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__containerPort; flux2-dev=8188; hidream-i1-dev-fp8=8188; comparison=same numeric value; source=resolved deployment config
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__webUIPort; flux2-dev=not-specified; hidream-i1-dev-fp8=not-specified; comparison=same value; source=resolved deployment config
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__volumeMountPath; flux2-dev=/data; hidream-i1-dev-fp8=/data; comparison=same value; source=resolved deployment config
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__recommendedInstance; flux2-dev=gpu-a100-80gb; hidream-i1-dev-fp8=gpu-a6000; comparison=different value; source=instanceConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__recommendedInstanceName; flux2-dev=GPU Very High VRAM (A100 80GB); hidream-i1-dev-fp8=GPU High VRAM (A6000); comparison=different value; source=instanceConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__recommendedInstanceSpecs; flux2-dev=70B+ LLMs, Complex Workflows, Fine-tuning; hidream-i1-dev-fp8=30B+ LLMs (quantized 70B), Video Gen, 48GB VRAM; comparison=different value; source=instanceConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__gpuType; flux2-dev=NVIDIA A100 80GB PCIe; hidream-i1-dev-fp8=NVIDIA RTX A6000; comparison=different value; source=instanceConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__gpuCount; flux2-dev=1; hidream-i1-dev-fp8=1; comparison=same numeric value; source=instanceConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__vramGB; flux2-dev=80; hidream-i1-dev-fp8=48; comparison=modelA higher by 32; source=instanceConfig.js derived fit
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__vCPU; flux2-dev=8; hidream-i1-dev-fp8=9; comparison=modelB higher by 1; source=instanceConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__ramGB; flux2-dev=117; hidream-i1-dev-fp8=50; comparison=modelA higher by 67; source=instanceConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__diskGB; flux2-dev=300; hidream-i1-dev-fp8=200; comparison=modelA higher by 100; source=instanceConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__instanceType; flux2-dev=gpu-very-high-vram; hidream-i1-dev-fp8=gpu-high-vram-value; comparison=different value; source=instanceConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__runpodInstanceId; flux2-dev=not-specified; hidream-i1-dev-fp8=not-specified; comparison=same value; source=instanceConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__hourlyCost; flux2-dev=1.39; hidream-i1-dev-fp8=0.49; comparison=modelA higher by 0.8999999999999999; source=instanceConfig.js deployCost
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__monthlyCost720h; flux2-dev=1000.8; hidream-i1-dev-fp8=352.8; comparison=modelA higher by 648; source=derived from hourly cost
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__deployTimeMinutes; flux2-dev=18; hidream-i1-dev-fp8=18; comparison=same numeric value; source=adapter estimate
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__popularity; flux2-dev=8; hidream-i1-dev-fp8=8; comparison=same numeric value; source=modelConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__groupPopularity; flux2-dev=98; hidream-i1-dev-fp8=85; comparison=modelA higher by 13; source=modelConfig.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__paramCount; flux2-dev=32B; hidream-i1-dev-fp8=17B; comparison=different value; source=parsed from model metadata
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__contextWindow; flux2-dev=not-specified; hidream-i1-dev-fp8=not-specified; comparison=same value; source=parsed from model metadata
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__description; flux2-dev=Full 32B model; Requires 48GB+ VRAM (H100); Maximum quality and fidelity;; hidream-i1-dev-fp8=17B parameter model with excellent prompt following; Uses Flux architecture;; comparison=different value; source=modelConfig.js / modelSeoData.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__useCases; flux2-dev=Multi-image editing workflows; Professional image generation; Fine-grained image control; Production-quality outputs; hidream-i1-dev-fp8=Prompt-accurate image generation; Creative illustration; Commercial image production; Fine-tuning base model; comparison=different value; source=modelSeoData.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__relatedGroups; flux2-dev=flux-2-klein; flux; hidream-i1; hidream-i1-dev-fp8=flux-2; qwen-image-2512; flux; comparison=different value; source=modelSeoData.js
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__sourceFiles; flux2-dev=src/config/modelConfig.js; src/config/modelSeoData.js; src/config/instanceConfig.js; hidream-i1-dev-fp8=src/config/modelConfig.js; src/config/modelSeoData.js; src/config/instanceConfig.js; comparison=same value; source=snapshot sync
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__aboutBlurb; flux2-dev=FLUX.2 is Black Forest Labs' 32B parameter model with multi-image editing capabilities; The Dev FP8 variant runs on RTX 4090/5090, while the full model requires 48GB+ VRAM for maximum quality;; hidream-i1-dev-fp8=HiDream I1 is a 17B parameter image generation model with excellent prompt following; Available in Dev, Full, and Fast variants with FP8 quantization for efficient deployment on consumer GPUs;; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__configKeys; flux2-dev=flux2-dev-fp8, flux2-dev, flux2-dev-q4; hidream-i1-dev-fp8=hidream-i1-dev-fp8, hidream-i1-full-fp8, hidream-i1-fast-fp8; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__defaultConfig.containerPort; flux2-dev=8188; hidream-i1-dev-fp8=8188; comparison=same numeric value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__defaultConfig.dockerImageBaseName; flux2-dev=comfyui-flux; hidream-i1-dev-fp8=comfyui-flux; comparison=same value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__defaultConfig.modelSize; flux2-dev=medium; hidream-i1-dev-fp8=medium; comparison=same value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__defaultConfig.templateName; flux2-dev=comfyui-flux; hidream-i1-dev-fp8=comfyui-flux; comparison=same value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__defaultConfig.volumeMountPath; flux2-dev=/data; hidream-i1-dev-fp8=/data; comparison=same value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__displayName; flux2-dev=FLUX.2; hidream-i1-dev-fp8=HiDream I1; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__dockerImageBaseName; flux2-dev=comfyui; hidream-i1-dev-fp8=comfyui; comparison=same value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__dockerImageTag; flux2-dev=flux2; hidream-i1-dev-fp8=hidream; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__groupPopularity; flux2-dev=98; hidream-i1-dev-fp8=85; comparison=modelA higher by 13; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__h1; flux2-dev=Deploy FLUX.2; hidream-i1-dev-fp8=Deploy HiDream I1; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__id; flux2-dev=flux2-dev; hidream-i1-dev-fp8=hidream-i1-dev-fp8; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__modelGroup; flux2-dev=flux2; hidream-i1-dev-fp8=hidream; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__modelSize; flux2-dev=xlarge; hidream-i1-dev-fp8=large; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__modelType; flux2-dev=image; hidream-i1-dev-fp8=image; comparison=same value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__name; flux2-dev=FLUX.2 Dev Full; hidream-i1-dev-fp8=HiDream I1 Dev FP8; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__popularity; flux2-dev=8; hidream-i1-dev-fp8=8; comparison=same numeric value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__recommendedInstance.deployCost; flux2-dev=1.39; hidream-i1-dev-fp8=0.49; comparison=modelA higher by 0.8999999999999999; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__recommendedInstance.disk; flux2-dev=300; hidream-i1-dev-fp8=200; comparison=modelA higher by 100; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__recommendedInstance.gpuCount; flux2-dev=1; hidream-i1-dev-fp8=1; comparison=same numeric value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__recommendedInstance.gpuType; flux2-dev=NVIDIA A100 80GB PCIe; hidream-i1-dev-fp8=NVIDIA RTX A6000; comparison=different value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__recommendedInstance.id; flux2-dev=gpu-a100-80gb; hidream-i1-dev-fp8=gpu-a6000; comparison=different value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__recommendedInstance.name; flux2-dev=GPU Very High VRAM (A100 80GB); hidream-i1-dev-fp8=GPU High VRAM (A6000); comparison=different value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__recommendedInstance.ram; flux2-dev=117; hidream-i1-dev-fp8=50; comparison=modelA higher by 67; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__recommendedInstance.suitableFor; flux2-dev=70B+ LLMs, Complex Workflows, Fine-tuning; hidream-i1-dev-fp8=30B+ LLMs (quantized 70B), Video Gen, 48GB VRAM; comparison=different value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__recommendedInstance.type; flux2-dev=gpu-very-high-vram; hidream-i1-dev-fp8=gpu-high-vram-value; comparison=different value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__recommendedInstance.vCPU; flux2-dev=8; hidream-i1-dev-fp8=9; comparison=modelB higher by 1; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__relatedGroups; flux2-dev=flux-2-klein, flux, hidream-i1; hidream-i1-dev-fp8=flux-2, qwen-image-2512, flux; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__resolvedConfig.containerPort; flux2-dev=8188; hidream-i1-dev-fp8=8188; comparison=same numeric value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__resolvedConfig.dockerImageBaseName; flux2-dev=comfyui; hidream-i1-dev-fp8=comfyui; comparison=same value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__resolvedConfig.modelSize; flux2-dev=xlarge; hidream-i1-dev-fp8=large; comparison=different value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__resolvedConfig.templateName; flux2-dev=comfyui-flux2; hidream-i1-dev-fp8=comfyui-hidream; comparison=different value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__resolvedConfig.volumeMountPath; flux2-dev=/data; hidream-i1-dev-fp8=/data; comparison=same value; source=resolved config snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__sizeVariant; flux2-dev=Dev Full (64GB); hidream-i1-dev-fp8=Dev FP8 (Recommended); comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__slug; flux2-dev=flux-2; hidream-i1-dev-fp8=hidream-i1; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__templateName; flux2-dev=comfyui-flux2; hidream-i1-dev-fp8=comfyui-hidream; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__useCases; flux2-dev=Multi-image editing workflows, Professional image generation, Fine-grained image control, Production-quality outputs; hidream-i1-dev-fp8=Prompt-accurate image generation, Creative illustration, Commercial image production, Fine-tuning base model; comparison=different value; source=model config or SEO snapshot
flux2-dev__hidream-i1-dev-fp8 field=flux2-dev__hidream-i1-dev-fp8__fact__workflowUrl; flux2-dev=https://comfyanonymous.github.io/ComfyUI_examples/flux2/; hidream-i1-dev-fp8=not-specified; comparison=different value; source=model config or SEO snapshot

Description comparison

Field	flux2-dev	hidream-i1-dev-fp8
Description	Full 32B model; Requires 48GB+ VRAM (H100); Maximum quality and fidelity;	17B parameter model with excellent prompt following; Uses Flux architecture;
Use cases	Multi-image editing workflows; Professional image generation; Fine-grained image control; Production-quality outputs	Prompt-accurate image generation; Creative illustration; Commercial image production; Fine-tuning base model
Related groups	flux-2-klein; flux; hidream-i1	flux-2; qwen-image-2512; flux

Deployment facts

flux2-dev__hidream-i1-dev-fp8 source id comparison: flux2-dev=flux2-dev; hidream-i1-dev-fp8=hidream-i1-dev-fp8;
flux2-dev__hidream-i1-dev-fp8 template comparison: flux2-dev uses comfyui-flux2 with comfyui; hidream-i1-dev-fp8 uses comfyui-hidream with comfyui;
flux2-dev__hidream-i1-dev-fp8 instance comparison: flux2-dev runs on GPU Very High VRAM (A100 80GB) at $1.39/hr and 80GB VRAM; hidream-i1-dev-fp8 runs on GPU High VRAM (A6000) at $0.49/hr and 48GB VRAM;
flux2-dev__hidream-i1-dev-fp8 fit notes: flux2-dev=70B+ LLMs, Complex Workflows, Fine-tuning; hidream-i1-dev-fp8=30B+ LLMs (quantized 70B), Video Gen, 48GB VRAM;
flux2-dev__hidream-i1-dev-fp8 use case comparison: flux2-dev=Multi-image editing workflows; Professional image generation; Fine-grained image control; Production-quality outputs; hidream-i1-dev-fp8=Prompt-accurate image generation; Creative illustration; Commercial image production; Fine-tuning base model;
flux2-dev__hidream-i1-dev-fp8 source files: flux2-dev=src/config/modelConfig.js, src/config/modelSeoData.js, src/config/instanceConfig.js; hidream-i1-dev-fp8=src/config/modelConfig.js, src/config/modelSeoData.js, src/config/instanceConfig.js;

Deployment payload fields

flux2-dev__hidream-i1-dev-fp8.candidate_a.modelType=image
flux2-dev__hidream-i1-dev-fp8.candidate_a.modelName=flux2-dev
flux2-dev__hidream-i1-dev-fp8.candidate_a.instanceId=gpu-a100-80gb
flux2-dev__hidream-i1-dev-fp8.candidate_a.templateName=comfyui-flux2
flux2-dev__hidream-i1-dev-fp8.candidate_a.containerPort=default
flux2-dev__hidream-i1-dev-fp8.candidate_a.dockerImageBaseName=comfyui
flux2-dev__hidream-i1-dev-fp8.candidate_b.modelType=image
flux2-dev__hidream-i1-dev-fp8.candidate_b.modelName=hidream-i1-dev-fp8
flux2-dev__hidream-i1-dev-fp8.candidate_b.instanceId=gpu-a6000
flux2-dev__hidream-i1-dev-fp8.candidate_b.templateName=comfyui-hidream
flux2-dev__hidream-i1-dev-fp8.candidate_b.containerPort=default
flux2-dev__hidream-i1-dev-fp8.candidate_b.dockerImageBaseName=comfyui

Matched model assets

flux2-dev__hidream-i1-dev-fp8 asset-1 filename=flux2_dev_fp8mixed.safetensors; size=32.2GB; type=unet; destination=diffusion_models; repository=Comfy-Org/flux2-dev; host=huggingface.co; url=https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/diffusion_models/flux2_dev_fp8mixed.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-2 filename=hidream_i1_dev_fp8.safetensors; size=17.1GB; type=unet; destination=diffusion_models; repository=Comfy-Org/HiDream-I1_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/resolve/main/split_files/diffusion_models/hidream_i1_dev_fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-3 filename=mistral_3_small_flux2_fp8.safetensors; size=18GB; type=clip; destination=text_encoders; repository=Comfy-Org/flux2-dev; host=huggingface.co; url=https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/text_encoders/mistral_3_small_flux2_fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-4 filename=flux2-dev-Q4_K_M.gguf; size=20.1GB; type=unet_gguf; destination=unet; repository=city96/FLUX.2-dev-gguf; host=huggingface.co; url=https://huggingface.co/city96/FLUX.2-dev-gguf/resolve/main/flux2-dev-Q4_K_M.gguf
flux2-dev__hidream-i1-dev-fp8 asset-5 filename=flux2-dev-Q5_K_M.gguf; size=24.1GB; type=unet_gguf; destination=unet; repository=city96/FLUX.2-dev-gguf; host=huggingface.co; url=https://huggingface.co/city96/FLUX.2-dev-gguf/resolve/main/flux2-dev-Q5_K_M.gguf
flux2-dev__hidream-i1-dev-fp8 asset-6 filename=flux2-dev-Q8_0.gguf; size=35GB; type=unet_gguf; destination=unet; repository=city96/FLUX.2-dev-gguf; host=huggingface.co; url=https://huggingface.co/city96/FLUX.2-dev-gguf/resolve/main/flux2-dev-Q8_0.gguf
flux2-dev__hidream-i1-dev-fp8 asset-7 filename=flux2-dev.safetensors; size=64.4GB; type=unet; destination=diffusion_models; repository=black-forest-labs/FLUX.2-dev; host=huggingface.co; url=https://huggingface.co/black-forest-labs/FLUX.2-dev/resolve/main/flux2-dev.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-8 filename=flux2-vae.safetensors; size=336MB; type=vae; destination=vae; repository=Comfy-Org/flux2-dev; host=huggingface.co; url=https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/vae/flux2-vae.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-9 filename=hidream_i1_dev_bf16.safetensors; size=34.2GB; type=unet; destination=diffusion_models; repository=Comfy-Org/HiDream-I1_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/resolve/main/split_files/diffusion_models/hidream_i1_dev_bf16.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-10 filename=hidream_i1_fast_fp8.safetensors; size=17.1GB; type=unet; destination=diffusion_models; repository=Comfy-Org/HiDream-I1_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/resolve/main/split_files/diffusion_models/hidream_i1_fast_fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-11 filename=hidream_i1_full_fp8.safetensors; size=17.1GB; type=unet; destination=diffusion_models; repository=Comfy-Org/HiDream-I1_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/resolve/main/split_files/diffusion_models/hidream_i1_full_fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-12 filename=mistral_3_small_flux2_bf16.safetensors; size=36GB; type=clip; destination=text_encoders; repository=Comfy-Org/flux2-dev; host=huggingface.co; url=https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/text_encoders/mistral_3_small_flux2_bf16.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-13 filename=flux-2-klein-9b-fp8.safetensors; size=9.43GB; type=unet; destination=diffusion_models; repository=black-forest-labs/FLUX.2-klein-9b-fp8; host=huggingface.co; url=https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-fp8/resolve/main/flux-2-klein-9b-fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-14 filename=flux1-dev-fp8.safetensors; size=11.9GB; type=unet; destination=unet; repository=Kijai/flux-fp8; host=huggingface.co; url=https://huggingface.co/Kijai/flux-fp8/resolve/main/flux1-dev-fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-15 filename=flux1-dev-kontext_fp8_scaled.safetensors; size=11.09GB; type=unet; destination=diffusion_models; repository=Comfy-Org/flux1-kontext-dev_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/flux1-kontext-dev_ComfyUI/resolve/main/split_files/diffusion_models/flux1-dev-kontext_fp8_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-16 filename=flux1-kontext-dev-fp8.safetensors; size=11.9GB; type=unet; destination=unet; repository=6chan/flux1-kontext-dev-fp8; host=huggingface.co; url=https://huggingface.co/6chan/flux1-kontext-dev-fp8/resolve/main/flux1-kontext-dev-fp8-e4m3fn.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-17 filename=hidream_i1_full_fp16.safetensors; size=34.2GB; type=unet; destination=diffusion_models; repository=Comfy-Org/HiDream-I1_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/resolve/main/split_files/diffusion_models/hidream_i1_full_fp16.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-18 filename=llama_3.1_8b_instruct_fp8_scaled.safetensors; size=9.08GB; type=clip; destination=clip; repository=Comfy-Org/HiDream-I1_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/resolve/main/split_files/text_encoders/llama_3.1_8b_instruct_fp8_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-19 filename=qwen_3_8b_fp8mixed.safetensors; size=4.4GB; type=clip; destination=text_encoders; repository=Comfy-Org/flux2-klein; host=huggingface.co; url=https://huggingface.co/Comfy-Org/flux2-klein/resolve/main/split_files/text_encoders/qwen_3_8b_fp8mixed.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-20 filename=ae.safetensors; size=335MB; type=vae; destination=vae; repository=black-forest-labs/FLUX.1-dev; host=huggingface.co; url=https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-21 filename=clip_g_hidream.safetensors; size=1.39GB; type=clip; destination=clip; repository=Comfy-Org/HiDream-I1_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/resolve/main/split_files/text_encoders/clip_g_hidream.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-22 filename=clip_l_hidream.safetensors; size=248MB; type=clip; destination=clip; repository=Comfy-Org/HiDream-I1_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/resolve/main/split_files/text_encoders/clip_l_hidream.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-23 filename=flux1-dev.safetensors; size=23.8GB; type=unet; destination=unet; repository=black-forest-labs/FLUX.1-dev; host=huggingface.co; url=https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/flux1-dev.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-24 filename=flux1-fill-dev.safetensors; size=23.8GB; type=unet; destination=unet; repository=black-forest-labs/FLUX.1-Fill-dev; host=huggingface.co; url=https://huggingface.co/black-forest-labs/FLUX.1-Fill-dev/resolve/main/flux1-fill-dev.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-25 filename=flux1-kontext-dev.safetensors; size=23.8GB; type=unet; destination=unet; repository=black-forest-labs/FLUX.1-Kontext-dev; host=huggingface.co; url=https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev/resolve/main/flux1-kontext-dev.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-26 filename=flux1-redux-dev.safetensors; size=182MB; type=style; destination=style_models; repository=black-forest-labs/FLUX.1-Redux-dev; host=huggingface.co; url=https://huggingface.co/black-forest-labs/FLUX.1-Redux-dev/resolve/main/flux1-redux-dev.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-27 filename=gemma_3_12b_it_fp8_e4m3fn.safetensors; size=12.8GB; type=clip; destination=text_encoders; repository=Lightricks/LTX-Video-2-0.9.5-DEV; host=huggingface.co; url=https://huggingface.co/Lightricks/LTX-Video-2-0.9.5-DEV/resolve/main/gemma_3_12B_it_fp8_e4m3fn.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-28 filename=ip-adapter_flux.safetensors; size=1.58GB; type=ip_adapter; destination=ipadapter; repository=InstantX/FLUX.1-dev-IP-Adapter; host=huggingface.co; url=https://huggingface.co/InstantX/FLUX.1-dev-IP-Adapter/resolve/main/ip-adapter.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-29 filename=ltx-2-19b-dev-fp8.safetensors; size=9.59GB; type=checkpoint; destination=checkpoints; repository=Lightricks/LTX-Video-2-0.9.5-DEV; host=huggingface.co; url=https://huggingface.co/Lightricks/LTX-Video-2-0.9.5-DEV/resolve/main/ltx-video-2-0.9.5-dev-fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-30 filename=ltx-2.3-22b-dev-fp8.safetensors; size=29.2GB; type=checkpoint; destination=checkpoints; repository=Lightricks/LTX-2.3-fp8; host=huggingface.co; url=https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-dev-fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-31 filename=sulphur_dev_fp8mixed.safetensors; size=29.2GB; type=checkpoint; destination=checkpoints; repository=SulphurAI/Sulphur-2-base; host=huggingface.co; url=https://huggingface.co/SulphurAI/Sulphur-2-base/resolve/main/sulphur_dev_fp8mixed.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-32 filename=t5xxl_fp8_e4m3fn_scaled.safetensors; size=5.16GB; type=clip; destination=clip; repository=comfyanonymous/flux_text_encoders; host=huggingface.co; url=https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-33 filename=t5xxl_fp8_e4m3fn.safetensors; size=4.89GB; type=clip; destination=clip; repository=comfyanonymous/flux_text_encoders; host=huggingface.co; url=https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-34 filename=Claymation.safetensors; size=353MB; type=lora; destination=loras; repository=vrgamedevgirl84/LTX_2.3_Clay_Mation_Style_LoRa; host=huggingface.co; url=https://huggingface.co/vrgamedevgirl84/LTX_2.3_Clay_Mation_Style_LoRa/resolve/main/Claymation.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-35 filename=clip_l.safetensors; size=246MB; type=clip; destination=clip; repository=comfyanonymous/flux_text_encoders; host=huggingface.co; url=https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-36 filename=flux1-schnell.safetensors; size=23.8GB; type=unet; destination=unet; repository=black-forest-labs/FLUX.1-schnell; host=huggingface.co; url=https://huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/flux1-schnell.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-37 filename=llava_llama3_fp8_scaled.safetensors; size=4.9GB; type=clip; destination=text_encoders; repository=Comfy-Org/HunyuanVideo_repackaged; host=huggingface.co; url=https://huggingface.co/Comfy-Org/HunyuanVideo_repackaged/resolve/main/split_files/text_encoders/llava_llama3_fp8_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-38 filename=ltx-2-19b-distilled-fp8.safetensors; size=27.1GB; type=checkpoint; destination=checkpoints; repository=Lightricks/LTX-2; host=huggingface.co; url=https://huggingface.co/Lightricks/LTX-2/resolve/main/ltx-2-19b-distilled-fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-39 filename=ltx-2.3-22b-dev.safetensors; size=46.1GB; type=checkpoint; destination=checkpoints; repository=Lightricks/LTX-2.3; host=huggingface.co; url=https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-22b-dev.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-40 filename=ltx-2.3-22b-distilled-fp8.safetensors; size=29.5GB; type=checkpoint; destination=checkpoints; repository=Lightricks/LTX-2.3-fp8; host=huggingface.co; url=https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-distilled-fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-41 filename=LTX2.3_Crisp_Enhance.safetensors; size=705MB; type=lora; destination=loras; repository=vrgamedevgirl84/LTX_2.3_Crisp_Enhance_Style_LoRa; host=huggingface.co; url=https://huggingface.co/vrgamedevgirl84/LTX_2.3_Crisp_Enhance_Style_LoRa/resolve/main/LTX2.3_Crisp_Enhance.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-42 filename=LTX2.3_Soft_Enhance.safetensors; size=353MB; type=lora; destination=loras; repository=vrgamedevgirl84/LTX_2.3_Soft_Enhance_Style_LoRa; host=huggingface.co; url=https://huggingface.co/vrgamedevgirl84/LTX_2.3_Soft_Enhance_Style_LoRa/resolve/main/LTX2.3_Soft_Enhance.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-43 filename=Luxe_Sensual.safetensors; size=353MB; type=lora; destination=loras; repository=vrgamedevgirl84/LTX_2.3_Luxe_Sensual_Style_LoRa; host=huggingface.co; url=https://huggingface.co/vrgamedevgirl84/LTX_2.3_Luxe_Sensual_Style_LoRa/resolve/main/Luxe_Sensual.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-44 filename=qwen_2.5_vl_7b_fp8_scaled.safetensors; size=9.38GB; type=clip; destination=text_encoders; repository=Comfy-Org/Qwen-Image_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-45 filename=qwen_3_4b-engineer-v4-fp8.safetensors; size=4.02GB; type=clip; destination=text_encoders; repository=SeeSee21/Z-Anime; host=huggingface.co; url=https://huggingface.co/SeeSee21/Z-Anime/resolve/main/text_encoder/qwen_3_4b-engineer-v4-fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-46 filename=qwen_image_edit_2509_fp8_e4m3fn.safetensors; size=19.03GB; type=unet; destination=diffusion_models; repository=Comfy-Org/Qwen-Image-Edit_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_edit_2509_fp8_e4m3fn.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-47 filename=qwen_image_edit_2509_fp8mixed.safetensors; size=19.12GB; type=unet; destination=diffusion_models; repository=Comfy-Org/Qwen-Image-Edit_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_edit_2509_fp8mixed.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-48 filename=qwen_image_edit_2511_fp8_e4m3fn.safetensors; size=20.4GB; type=unet; destination=diffusion_models; repository=drbaph/Qwen-Image-Edit-2511-FP8; host=huggingface.co; url=https://huggingface.co/drbaph/Qwen-Image-Edit-2511-FP8/resolve/main/qwen_image_edit_2511_fp8_e4m3fn.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-49 filename=qwen_image_edit_2511_fp8mixed.safetensors; size=19.12GB; type=unet; destination=diffusion_models; repository=Comfy-Org/Qwen-Image-Edit_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_edit_2511_fp8mixed.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-50 filename=qwen_image_edit_fp8_e4m3fn.safetensors; size=10.7GB; type=unet; destination=diffusion_models; repository=Comfy-Org/Qwen-Image-Edit_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_edit_fp8_e4m3fn.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-51 filename=qwen_image_fp8_e4m3fn.safetensors; size=10.7GB; type=unet; destination=diffusion_models; repository=Comfy-Org/Qwen-Image_ComfyUI; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_fp8_e4m3fn.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-52 filename=qwen3_4b_fp8_scaled.safetensors; size=4.11GB; type=clip; destination=text_encoders; repository=jiangchengchengNLP/qwen3-4b-fp8-scaled; host=huggingface.co; url=https://huggingface.co/jiangchengchengNLP/qwen3-4b-fp8-scaled/resolve/main/qwen3_4b_fp8_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-53 filename=sd3_medium_incl_clips_t5xxlfp8.safetensors; size=5.58GB; type=checkpoint; destination=checkpoints; repository=stabilityai/stable-diffusion-3-medium; host=huggingface.co; url=https://huggingface.co/stabilityai/stable-diffusion-3-medium/resolve/main/sd3_medium_incl_clips_t5xxlfp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-54 filename=sd3.5_large_fp8_scaled.safetensors; size=8.3GB; type=checkpoint; destination=checkpoints; repository=stabilityai/stable-diffusion-3.5-large; host=huggingface.co; url=https://huggingface.co/stabilityai/stable-diffusion-3.5-large/resolve/main/sd3.5_large_fp8_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-55 filename=seedvr2_ema_3b_fp8_e4m3fn.safetensors; size=3.39GB; type=unet; destination=diffusion_models; repository=numz/SeedVR2_comfyUI; host=huggingface.co; url=https://huggingface.co/numz/SeedVR2_comfyUI/resolve/main/seedvr2_ema_3b_fp8_e4m3fn.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-56 filename=seedvr2_ema_7b_fp8_e4m3fn.safetensors; size=8.24GB; type=unet; destination=diffusion_models; repository=numz/SeedVR2_comfyUI; host=huggingface.co; url=https://huggingface.co/numz/SeedVR2_comfyUI/resolve/main/seedvr2_ema_7b_fp8_e4m3fn.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-57 filename=sulphur_dev_bf16.safetensors; size=46.1GB; type=checkpoint; destination=checkpoints; repository=SulphurAI/Sulphur-2-base; host=huggingface.co; url=https://huggingface.co/SulphurAI/Sulphur-2-base/resolve/main/sulphur_dev_bf16.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-58 filename=t5xxl_fp16.safetensors; size=9.79GB; type=clip; destination=clip; repository=comfyanonymous/flux_text_encoders; host=huggingface.co; url=https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-59 filename=ultra_ae.safetensors; size=335MB; type=vae; destination=vae; repository=Owen777/UltraFlux-v1; host=huggingface.co; url=https://huggingface.co/Owen777/UltraFlux-v1/resolve/main/vae/diffusion_pytorch_model.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-60 filename=UltraFlux-v1_model.safetensors; size=335MB; type=vae; destination=vae; repository=Owen777/UltraFlux-v1; host=huggingface.co; url=https://huggingface.co/Owen777/UltraFlux-v1/resolve/main/vae/diffusion_pytorch_model.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-61 filename=umt5_xxl_fp8_e4m3fn_scaled.safetensors; size=4.9GB; type=clip; destination=text_encoders; repository=Comfy-Org/Wan_2.1_ComfyUI_repackaged; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-62 filename=Wan2_2-Animate-14B_fp8_e4m3fn_scaled_KJ.safetensors; size=18.4GB; type=unet; destination=diffusion_models; repository=Kijai/WanVideo_comfy_fp8_scaled; host=huggingface.co; url=https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/resolve/main/Wan22Animate/Wan2_2-Animate-14B_fp8_e4m3fn_scaled_KJ.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-63 filename=Wan2_2-Animate-14B_fp8_scaled_e4m3fn_KJ_v2.safetensors; size=17.3GB; type=unet; destination=diffusion_models; repository=Kijai/WanVideo_comfy_fp8_scaled; host=huggingface.co; url=https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/resolve/main/Wan22Animate/Wan2_2-Animate-14B_fp8_scaled_e4m3fn_KJ_v2.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-64 filename=wan2.1_t2v_14B_fp8_e4m3fn.safetensors; size=14.3GB; type=unet; destination=diffusion_models; repository=Comfy-Org/Wan_2.1_ComfyUI_repackaged; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_t2v_14B_fp8_e4m3fn.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-65 filename=wan2.2_fun_camera_high_noise_14B_fp8_scaled.safetensors; size=14.25GB; type=unet; destination=diffusion_models; repository=Comfy-Org/Wan_2.2_ComfyUI_Repackaged; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_fun_camera_high_noise_14B_fp8_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-66 filename=wan2.2_fun_control_high_noise_14B_fp8_scaled.safetensors; size=13.31GB; type=unet; destination=diffusion_models; repository=Comfy-Org/Wan_2.2_ComfyUI_Repackaged; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_fun_control_high_noise_14B_fp8_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-67 filename=wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors; size=13.31GB; type=unet; destination=diffusion_models; repository=Comfy-Org/Wan_2.2_ComfyUI_Repackaged; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-68 filename=wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors; size=13.31GB; type=unet; destination=diffusion_models; repository=Comfy-Org/Wan_2.2_ComfyUI_Repackaged; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-69 filename=wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors; size=14.2GB; type=unet; destination=diffusion_models; repository=Comfy-Org/Wan_2.2_ComfyUI_Repackaged; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-70 filename=wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors; size=14.2GB; type=unet; destination=diffusion_models; repository=Comfy-Org/Wan_2.2_ComfyUI_Repackaged; host=huggingface.co; url=https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-71 filename=z_image_turbo_fp8.safetensors; size=6.15GB; type=unet; destination=diffusion_models; repository=Comfy-Org/z_image_turbo; host=huggingface.co; url=https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-72 filename=z-anime-base-fp8.safetensors; size=6.15GB; type=unet; destination=diffusion_models; repository=SeeSee21/Z-Anime; host=huggingface.co; url=https://huggingface.co/SeeSee21/Z-Anime/resolve/main/diffusion_models/z-anime-base-fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-73 filename=z-anime-distill-4step-fp8.safetensors; size=6.15GB; type=unet; destination=diffusion_models; repository=SeeSee21/Z-Anime; host=huggingface.co; url=https://huggingface.co/SeeSee21/Z-Anime/resolve/main/diffusion_models/z-anime-distill-4step-fp8.safetensors
flux2-dev__hidream-i1-dev-fp8 asset-74 filename=z-anime-distill-8step-fp8.safetensors; size=6.15GB; type=unet; destination=diffusion_models; repository=SeeSee21/Z-Anime; host=huggingface.co; url=https://huggingface.co/SeeSee21/Z-Anime/resolve/main/diffusion_models/z-anime-distill-8step-fp8.safetensors

Paired source evidence

flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=id; value=flux2-dev
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=name; value=FLUX.2 Dev Full
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=displayName; value=FLUX.2
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=sizeVariant; value=Dev Full (64GB)
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=templateName; value=comfyui-flux2
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=dockerImageBaseName; value=comfyui
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=dockerImageTag; value=flux2
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=modelSize; value=xlarge
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=popularity; value=8
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=modelGroup; value=flux2
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=groupPopularity; value=98
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=h1; value=Deploy FLUX.2
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=aboutBlurb; value=FLUX.2 is Black Forest Labs' 32B parameter model with multi-image editing capabilities; The Dev FP8 variant runs on RTX 4090/5090, while the full model requires 48GB+ VRAM for maximum quality;
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=useCases; value=Multi-image editing workflows, Professional image generation, Fine-grained image control, Production-quality outputs
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=relatedGroups; value=flux-2-klein, flux, hidream-i1
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=configKeys; value=flux2-dev-fp8, flux2-dev, flux2-dev-q4
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=workflowUrl; value=https://comfyanonymous.github.io/ComfyUI_examples/flux2/
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=defaultConfig.templateName; value=comfyui-flux
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=defaultConfig.dockerImageBaseName; value=comfyui-flux
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=defaultConfig.containerPort; value=8188
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=defaultConfig.volumeMountPath; value=/data
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=defaultConfig.modelSize; value=medium
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=resolvedConfig.templateName; value=comfyui-flux2
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=resolvedConfig.dockerImageBaseName; value=comfyui
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=resolvedConfig.containerPort; value=8188
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=resolvedConfig.volumeMountPath; value=/data
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=resolvedConfig.modelSize; value=xlarge
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=recommendedInstance.id; value=gpu-a100-80gb
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=recommendedInstance.name; value=GPU Very High VRAM (A100 80GB)
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=recommendedInstance.suitableFor; value=70B+ LLMs, Complex Workflows, Fine-tuning
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=recommendedInstance.vCPU; value=8
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=recommendedInstance.ram; value=117
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=recommendedInstance.disk; value=300
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=recommendedInstance.gpuType; value=NVIDIA A100 80GB PCIe
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=recommendedInstance.gpuCount; value=1
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=recommendedInstance.type; value=gpu-very-high-vram
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=recommendedInstance.deployCost; value=1.39
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=slug; value=flux-2
flux2-dev__hidream-i1-dev-fp8 source-model=flux2-dev; field=modelType; value=image
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=id; value=hidream-i1-dev-fp8
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=name; value=HiDream I1 Dev FP8
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=displayName; value=HiDream I1
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=sizeVariant; value=Dev FP8 (Recommended)
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=templateName; value=comfyui-hidream
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=dockerImageBaseName; value=comfyui
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=dockerImageTag; value=hidream
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=modelSize; value=large
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=popularity; value=8
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=modelGroup; value=hidream
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=groupPopularity; value=85
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=h1; value=Deploy HiDream I1
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=aboutBlurb; value=HiDream I1 is a 17B parameter image generation model with excellent prompt following; Available in Dev, Full, and Fast variants with FP8 quantization for efficient deployment on consumer GPUs;
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=useCases; value=Prompt-accurate image generation, Creative illustration, Commercial image production, Fine-tuning base model
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=relatedGroups; value=flux-2, qwen-image-2512, flux
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=configKeys; value=hidream-i1-dev-fp8, hidream-i1-full-fp8, hidream-i1-fast-fp8
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=defaultConfig.templateName; value=comfyui-flux
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=defaultConfig.dockerImageBaseName; value=comfyui-flux
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=defaultConfig.containerPort; value=8188
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=defaultConfig.volumeMountPath; value=/data
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=defaultConfig.modelSize; value=medium
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=resolvedConfig.templateName; value=comfyui-hidream
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=resolvedConfig.dockerImageBaseName; value=comfyui
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=resolvedConfig.containerPort; value=8188
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=resolvedConfig.volumeMountPath; value=/data
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=resolvedConfig.modelSize; value=large
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=recommendedInstance.id; value=gpu-a6000
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=recommendedInstance.name; value=GPU High VRAM (A6000)
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=recommendedInstance.suitableFor; value=30B+ LLMs (quantized 70B), Video Gen, 48GB VRAM
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=recommendedInstance.vCPU; value=9
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=recommendedInstance.ram; value=50
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=recommendedInstance.disk; value=200
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=recommendedInstance.gpuType; value=NVIDIA RTX A6000
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=recommendedInstance.gpuCount; value=1
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=recommendedInstance.type; value=gpu-high-vram-value
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=recommendedInstance.deployCost; value=0.49
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=slug; value=hidream-i1
flux2-dev__hidream-i1-dev-fp8 source-model=hidream-i1-dev-fp8; field=modelType; value=image

Pair-scoped catalog context

FAQ

What GPU runs flux2-dev in the flux2-dev vs hidream-i1-dev-fp8 comparison?

For flux2-dev vs hidream-i1-dev-fp8, flux2-dev uses GPU Very High VRAM (A100 80GB) with 80GB VRAM at $1.39/hr.

What GPU runs hidream-i1-dev-fp8 in the flux2-dev vs hidream-i1-dev-fp8 comparison?

For flux2-dev vs hidream-i1-dev-fp8, hidream-i1-dev-fp8 uses GPU High VRAM (A6000) with 48GB VRAM at $0.49/hr.

Which is cheaper to run 24/7 for flux2-dev vs hidream-i1-dev-fp8?

For flux2-dev vs hidream-i1-dev-fp8, hidream-i1-dev-fp8 is cheaper at $352.80/month vs $1000.80/month.