Sourceful · text-to-image
1K · 2K · 4K tiers · 10 reference images
Benchmark v1.0 · 29 October 2026 · 26 models
Riverflow 2.0 Pro
Frontier arena leader for design-heavy prompts.
- Best for producttied
- Technical qualitytied
- Aestheticstied
- Text rendering (OCR)tied
- Counts & placementtied
Benchmark record 12 prompts · v1.0
Accumulated benchmark v1.0 · price list
Five ways of judging rank out of 26
Adherence, technical and aesthetics come from a blind vision-model judge; text and counts are objective checks. The overall index blends the first three 50/30/20.
Profile by prompt type axis 90–100
Output map every render, unretouched












AI-generated. First result returned, no retries, no editing.
Against the field Riverflow 2.0 Pro vs median · axis 90–100
Reading the card
Riverflow 2.0 Pro finishes 9th of 26 on the overall index at 95.7.
Its strongest kind of prompt is product (97.5 against a field median of 96.5); its weakest is people (94 against 95).
OCR found the exact words in 100% of the text prompts and 100% of the count, colour and placement checks passed.
A render takes a median 59.1 s, 25th of 26 for speed and slower than the field median of 20.3 s, and costs 3 credits (about $0.57 on the Premium plan), which puts it 25th of 26 on quality per credit.
Pick it for
- Product97.5 · 8th of 26 · clean studio lighting, material fidelity, catalogue framing
- Illustration96.5 · 2nd of 26 · holding a named art style with clean shapes and palette
- Composition95 · 13th of 26 · object counts, colours and left/right placement
Weigh up
- People94 · 23rd of 26 · skin, hands, eyes and natural light on a human subject
- Speed59.1 s median is slower than the field’s 20.3 s
- Price3 credits per image, 23rd of 26 on price; 16 models in the index cost one
Nearest rivals closest overall scores
In the studio what you can set
- Vendor
- Sourceful
- Resolution tiers
- 1K, 2K, 4K
- Highest output
- 1K
- Reference images
- Up to 10
- Images per request
- 1
- Seed
- No
- Negative prompt
- No
- Base price
- 3 credits · ≈ $0.57
Questions about Riverflow 2.0 Pro
- Is Riverflow 2.0 Pro good at rendering text in images?
- In benchmark v1.0 the OCR check found the exact requested phrase in 100% of Riverflow 2.0 Pro's text-prompt renders, and the blind judge gave its text category 96 out of 100 (field median 95.5). Every word came out exactly as written.
- How fast is Riverflow 2.0 Pro?
- Median 59.1 seconds from submit to finished image across the 12 benchmark prompts, with the slowest tenth at 123.5 seconds. That is 25th of 26 models; the field median is 20.3 seconds.
- How much does Riverflow 2.0 Pro cost per image?
- 3 credits at the base 1K tier, about $0.57 at the Premium plan rate of $0.19 per credit. Higher resolution tiers (2K, 4K) can cost more; see pricing.
- Riverflow 2.0 Pro or WAN 2.7 Pro?
- WAN 2.7 Pro scores 95.8 overall against 95.7 for Riverflow 2.0 Pro, inside the judge’s noise, so treat them as equal on quality and decide on speed and price. Riverflow 2.0 Pro renders in 59.1 s for 3 credits; WAN 2.7 Pro in 48.6 s for 2 credits.
- What is Riverflow 2.0 Pro best used for?
- It ranks in the top three for illustration prompts in this run. Frontier arena leader for design-heavy prompts.
- How long has Riverflow 2.0 Pro been at the top?
- Riverflow 2.0 Pro is currently 9th; its best rank across 1 benchmark run is #9, and it has been in the top 10 for 1 week.
- How were these numbers measured?
- Every model rendered the same 12 prompts at matched settings. A vision-model judge scored each image blind on adherence, technical quality and aesthetics (blended 50/30/20 into the overall index); OCR and fixed yes/no checks measured text accuracy and composition without a judge. Seconds were timed through the production API. Benchmark v1.0, 29 October 2026.
