MODEL · HIDREAM · 8B DENSE (PIXEL-SPACE; NO VAE, NO DISJOINT TEXT ENCODER)
HiDream-O1-Image (8B)
HiDream's next-generation image foundation model. The architectural story: pixel-space generation without an external VAE or disjoint text encoder — one Pixel-level Unified Transformer handles text-to-image, image editing, subject-driven personalization, and storyboarding in a single weight set. Debuted at #8 on Artificial Analysis T2I Arena at launch. Supersedes HiDream-I1 for the MIT-license open-weight slot.
License: MIT · Context: Up to 2,048 × 2,048 native; T2I + edit + subject-driven personalization in a single model · Released: May 8, 2026
The decision in five lines
- The call
- Buy — for image
- Best for
- image
- Runs on
- 23 hardware picks fit (cheapest: Intel Arc B580 12 GB · $249)
- Watch out
- When you need the absolute top of T2I quality — Google Imagen 4 + Black Forest FLUX.2 still edge it on complex compositions per Artificial Analysis Arena rankings.
- Evidence
- Estimated
- 8B dense (pixel-space; no VAE, no disjoint text encoder)
- PARAMETERS
- IMAGE GEN
- TYPE
- Up
- CONTEXT
- ~5 GB (full) / smaller for distilled Dev variant
- VRAM AT Q4
Where we recommend this
Every tier slot in the planner where this model is a top or alternate pick. Pulled live from planner.js — when the planner refreshes, this table stays current.
The call
HiDream's next-generation image foundation model. The architectural story: pixel-space generation without an external VAE or disjoint text encoder — one Pixel-level Unified Transformer handles text-to-image, image editing, subject-driven personalization, and storyboarding in a single weight set. Debuted at #8 on Artificial Analysis T2I Arena at launch. Supersedes HiDream-I1 for the MIT-license open-weight slot.
When not to use: When you need the absolute top of T2I quality — Google Imagen 4 + Black Forest FLUX.2 still edge it on complex compositions per Artificial Analysis Arena rankings. Also: at 8B with no VAE, it's a different architecture from FLUX/SDXL — existing ComfyUI custom-node graphs may not port cleanly.
Runner notes
Available on HuggingFace as `HiDream-ai/HiDream-O1-Image` (full) and `HiDream-ai/HiDream-O1-Image-Dev` (distilled, faster). Includes a Reasoning-Driven Prompt Agent for prompt enhancement. Both variants share the UiT architecture.
Hardware that fits
Every hardware pick whose memory fits this model at the quant we recommend. Sorted cheapest-first — the top row is your best-value fit. Click through for the full buyer’s guide.
- Intel Arc B580 12 GBPerfect · 1.9× 12 GB · $249–$299
- NVIDIA RTX 3060 12 GBPerfect · 1.9× 12 GB · $250–$340
- Minisforum UM890 ProPerfect · 3.9× 32 GB DDR5 (shared) · $463–$580 all-in
- RTX 5060 Ti 16 GBPerfect · 2.6× 16 GB · $560–$610
- AMD Radeon RX 9070 XTPerfect · 2.6× 16 GB · $649–$849
- AMD Radeon RX 7900 XTXPerfect · 3.9× 24 GB · $770–$1,400
- Mac Mini M4 16 GBPerfect · 1.7× 16 GB unified · $799 (new floor) / $499–$599 (eBay/residuals)
- NVIDIA RTX 3090 (used, single)Perfect · 3.9× 24 GB · $800–$1,000
- NVIDIA RTX 5070 TiPerfect · 2.6× 16 GB · $980–$1,300
- NVIDIA RTX 5080Perfect · 2.6× 16 GB · $999–$1,250
- MacBook Air M5 24 GBPerfect · 2.6× 24 GB unified · $1,299–$1,699
- Mac Mini M4 Pro 24 GBPerfect · 2.6× 24 GB unified · $1,399
- Dual RTX 3090 (used)Perfect · 7.8× 48 GB · $1,800–$2,500 all-in
- Framework Desktop (Ryzen AI Max+ 395)Perfect · 13.9× 128 GB unified · $1,999–$2,851
- NVIDIA RTX 4090Perfect · 3.9× 24 GB · $2,200–$2,800
- M5 Pro MacBook Pro 48 GBPerfect · 5.2× 48 GB unified · $2,599–$3,099
- Mac Studio M4 Max 64 GBPerfect · 6.9× 64 GB unified · $3,199
- NVIDIA RTX A6000 (48 GB, used)Perfect · 7.8× 48 GB ECC · $3,500–$4,500
- NVIDIA RTX 5090Perfect · 5.2× 32 GB · $3,800–$4,100
- Mac Studio M3 Ultra 96 GBPerfect · 10.4× 96 GB unified · $3,999
- M5 Max MacBook Pro 64 GBPerfect · 6.9× 64 GB unified · $4,499
- NVIDIA DGX SparkPerfect · 13.9× 128 GB unified · $4,699
- Dual RTX 5090Perfect · 10.3× 64 GB (2×32) · $8,500–$10,500
Next step
Find-by-model — see what hardware runs this→