Skip to content
TheChatArchiveThe Chat Archive
Claudeclaude-sonnet-4-20250514· AnthropicHugging Face LMArena Human Preference 140K

create a table: rows: typical resolutions for AI image generation, increasing in size up…

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with Geminigemini-2.5-flash-lite-preview-06-17-thinking’s answer.
  1. User

    create a table: rows: typical resolutions for AI image generation, increasing in size up to 8K columns: typical customer gpus, increasing in performance fields: generation speed for Stable diffusion for a batch of 4 pictures

  2. Claude Assistant

    Here's a table showing estimated Stable Diffusion generation speeds (batch of 4 images) across different resolutions and GPU tiers:

    ResolutionRTX 3060 12GBRTX 3070 8GBRTX 4070 12GBRTX 4080 16GBRTX 4090 24GB
    512×51245-60s30-40s25-35s18-25s12-18s
    768×76890-120s60-80s50-70s35-50s25-35s
    1024×1024180-240s120-160s100-140s70-100s50-70s
    1536×1536400-500s270-350s220-300s160-220s110-160s
    2048×2048Out of VRAM450-600s380-520s280-380s200-280s
    4K (3840×2160)Out of VRAMOut of VRAMOut of VRAM600-800s450-600s
    8K (7680×4320)Out of VRAMOut of VRAMOut of VRAMOut of VRAM1800-2400s

    Notes:

    • Times assume SDXL model with 20-30 inference steps
    • "Out of VRAM" indicates insufficient memory for the resolution
    • Actual speeds vary significantly based on model, sampler, steps, and optimizations
    • Times include both positive and negative prompts
    • Performance can be improved with techniques like xFormers, half-precision, or model optimizations

    The RTX 4090 is the only consumer GPU that can reasonably handle 8K generation, though it requires substantial time and memory management.

  3. User

    Add also recent and price efficient AMD GPUs in the comparison

  4. Claude Assistant

    Here's the updated table including recent price-efficient AMD GPUs:

    ResolutionRTX 3060 12GBRX 6700 XT 12GBRTX 3070 8GBRX 7600 XT 16GBRTX 4070 12GBRX 7800 XT 16GBRTX 4080 16GBRX 7900 XTX 24GBRTX 4090 24GB
    512×51245-60s55-70s30-40s40-55s25-35s28-38s18-25s20-28s12-18s
    768×76890-120s110-140s60-80s80-110s50-70s55-75s35-50s40-55s25-35s
    1024×1024180-240s220-280s120-160s160-220s100-140s110-150s70-100s80-110s50-70s
    1536×1536400-500s480-600s270-350s350-450s220-300s240-320s160-220s180-240s110-160s
    2048×2048Out of VRAM800-1000s450-600s600-800s380-520s420-560s280-380s320-420s200-280s
    4K (3840×2160)Out of VRAMOut of VRAMOut of VRAM1200-1600sOut of VRAM900-1200s600-800s700-900s450-600s
    8K (7680×4320)Out of VRAMOut of VRAMOut of VRAMOut of VRAMOut of VRAMOut of VRAMOut of VRAM2400-3200s1800-2400s

    Key AMD GPU Notes:

    • RX 6700 XT: Excellent value for 1024×1024 and below, but slower than NVIDIA equivalents due to less optimized AI frameworks
    • RX 7600 XT: Strong VRAM advantage (16GB) allows higher resolutions than many NVIDIA cards
    • RX 7800 XT: Good performance with 16GB VRAM, competitive with RTX 4070 at higher resolutions
    • RX 7900 XTX: Best AMD option with 24GB VRAM, can handle 8K generation

    AMD Considerations:

    • AMD GPUs typically run 15-25% slower than NVIDIA equivalents due to CUDA optimizations in most AI frameworks
    • ROCm support is improving but still less mature than CUDA
    • Excellent VRAM-to-price ratio, especially for higher resolution work
    • Some Stable Diffusion implementations may require additional setup for AMD cards

    The RX 7600 XT and 7800 XT offer particularly strong value propositions for AI image generation due to their generous VRAM allocations.

  5. User

    update the table: Only show recent gpus and only two (amd and nvidia) for each memory size

  6. Claude Assistant

    Here's the updated table with recent GPUs organized by memory size:

    Resolution12GB VRAM16GB VRAM24GB VRAM
    RTX 4070RX 6700 XTRTX 4080RX 7800 XTRTX 4090RX 7900 XTX
    512×51225-35s55-70s18-25s28-38s12-18s20-28s
    768×76850-70s110-140s35-50s55-75s25-35s40-55s
    1024×1024100-140s220-280s70-100s110-150s50-70s80-110s
    1536×1536220-300s480-600s160-220s240-320s110-160s180-240s
    2048×2048380-520s800-1000s280-380s420-560s200-280s320-420s
    4K (3840×2160)Out of VRAMOut of VRAM600-800s900-1200s450-600s700-900s
    8K (7680×4320)Out of VRAMOut of VRAMOut of VRAMOut of VRAM1800-2400s2400-3200s

    Key Insights by Memory Tier:

    • 12GB: RTX 4070 significantly faster but both hit VRAM limits at 4K
    • 16GB: RTX 4080 faster at lower resolutions, but RX 7800 XT offers better value for high-resolution work
    • 24GB: RTX 4090 leads in speed, RX 7900 XTX provides more affordable 8K capability

    Notes:

    • Times assume SDXL model with 20-30 inference steps, batch of 4 images
    • AMD performance gap narrows at higher resolutions due to VRAM advantages
    • Both 24GB cards can handle 8K generation, though it's time-intensive
  7. User

    the 5090 and 32gb group is missing

  8. Claude Assistant

    Here's the updated table including the RTX 5090 and 32GB VRAM tier:

    Resolution12GB VRAM16GB VRAM24GB VRAM32GB VRAM
    RTX 4070RX 6700 XTRTX 4080RX 7800 XTRTX 4090RX 7900 XTXRTX 5090RX 7900 XTX
    512×51225-35s55-70s18-25s28-38s12-18s20-28s8-12s20-28s
    768×76850-70s110-140s35-50s55-75s25-35s40-55s15-25s40-55s
    1024×1024100-140s220-280s70-100s110-150s50-70s80-110s30-45s80-110s
    1536×1536220-300s480-600s160-220s240-320s110-160s180-240s70-100s180-240s
    2048×2048380-520s800-1000s280-380s420-560s200-280s320-420s120-180s320-420s
    4K (3840×2160)Out of VRAMOut of VRAM600-800s900-1200s450-600s700-900s280-400s700-900s
    8K (7680×4320)Out of VRAMOut of VRAMOut of VRAMOut of VRAM1800-2400s2400-3200s1200-1600s2400-3200s

    Notes on 32GB Tier:

    • RTX 5090: Latest flagship with 32GB VRAM, approximately 60-70% faster than RTX 4090
    • RX 7900 XTX: Listed again as AMD's current top option (24GB), no 32GB AMD consumer GPU available yet
    • RTX 5090's extra VRAM headroom allows for larger batch sizes or more complex models at high resolutions

    Key Advantages of 32GB VRAM:

    • Enables larger batch sizes (8+ images) at high resolutions
    • Supports more complex models and LoRAs simultaneously
    • Future-proofs for next-generation AI models requiring more memory
    • Allows comfortable 8K generation with memory to spare

    The RTX 5090 represents the current pinnacle of consumer AI generation performance, though at a significant price premium.

  9. User

    so the 4080 is faster then the rx 7900? Is 16gb really sufficient for 4k image generation?

  10. Claude Assistant

    You're right to question this - let me clarify both points:

    RTX 4080 vs RX 7900 XTX Speed: The RX 7900 XTX is actually faster in raw compute power, but NVIDIA cards benefit significantly from CUDA optimizations in AI frameworks. In practice:

    • RX 7900 XTX: ~61 TFLOPS compute, 24GB VRAM
    • RTX 4080: ~48 TFLOPS compute, 16GB VRAM

    The RTX 4080 appears faster in my table primarily due to software optimization advantages, not hardware superiority. With well-optimized ROCm setups, the RX 7900 XTX can match or exceed RTX 4080 performance.

    16GB for 4K Generation: 16GB is technically sufficient for 4K generation, but it's cutting it very close:

    • SDXL at 4K uses ~14-15GB VRAM
    • This leaves minimal headroom for system overhead
    • You might need to use optimizations like:
      • Model offloading
      • Reduced precision (fp16)
      • Smaller batch sizes
      • VAE tiling

    Realistic 4K Requirements:

    • Comfortable: 20GB+ VRAM
    • Workable: 16GB with optimizations
    • Tight but possible: 12GB with aggressive memory management

    The RTX 4080 can do 4K, but the RX 7900 XTX's extra 8GB VRAM makes it much more comfortable for sustained 4K work, despite potentially slower individual inference times due to software optimization differences.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.